{ "complete": true, "report": { "bucket": "emo_Bitterness", "label": "Intense Bitterness", "definition": { "id": "emo_Bitterness", "category": "emotion", "head": "emo_Bitterness", "pole": "high", "label": "Intense Bitterness", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_bitterness/full-v2-sealed/sealed-selected", "mission": "emotion_bitterness", "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": 6.276461405754089, "genuineness": 4.456322894096375, "wer": 0.011582569360238992, "identity": 0.6353771591186523, "voiceclap": -0.054716720134019854, "fitness": 0.6085760637358525, "steering_v2": 0.5477635928416614, "raw_target": 0.3265976847708225, "target_cdf": 0.5477635928416614, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.288137130737304, "genuineness": 4.422871618270874, "wer": 0.011494072492960146, "identity": 0.6353771591186523, "fitness": 0.6132487914128426, "steering_v2": 0.5600192184522522 }, "none": { "n": 50, "ce": 6.264785680770874, "genuineness": 4.489774169921875, "wer": 0.01167106622751784, "identity": null, "fitness": 0.6039033360588623, "steering_v2": 0.5355079672310706 } } } } ], "selected_wording": { "id": "manual-564f1f7c16dd", "general": "Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.", "inline": [ "Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.", "Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.", "Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure." ], "cfg": 3, "recipe": "P05", "strategy": "local-Gemma-mutation", "timing_syntax": "canonical", "canonical_labels": true, "neutral_event": "keep", "parent": "cfg-3", "origin": "exact_frozen_manual_recipe" }, "selection": { "manual_no_adapter": { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": -0.184179688916117, "target_raw": 0.14452182091772556, "ce": 5.918961715698242, "genuineness": 4.564772844314575, "identity": 0.5143115244805813, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.042916452139616014, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": -0.1845214813103226, "target_raw": 0.14438273645937444, "ce": 5.858746361732483, "genuineness": 4.510171389579773, "identity": 0.5630354374647141, "wer": 0.022978801169590644, "valid_fraction": 0.95, "identity_delta": 0.005807460844516754, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": -0.184179688916117, "target_raw": 0.14452182091772556, "ce": 5.918961715698242, "genuineness": 4.564772844314575, "identity": 0.5143115244805813, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.042916452139616014, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": -0.23007812617294537, "target_raw": 0.1258445203304291, "ce": 5.9729719161987305, "genuineness": 4.603370547294617, "identity": 0.533838314563036, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.02338966205716133, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": -0.2568359376001295, "target_raw": 0.11495605185627937, "ce": 6.005338335037232, "genuineness": 4.58297336101532, "identity": 0.5886952176690101, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.03146724104881286, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": -0.33154296902893216, "target_raw": 0.08455576449632644, "ce": 6.116337132453919, "genuineness": 4.558183002471924, "identity": 0.5915812708437442, "wer": 0.00804093567251462, "valid_fraction": 1, "identity_delta": 0.03435329422354698, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": -0.3475585964606482, "target_raw": 0.07803857773542404, "ce": 6.111770129203796, "genuineness": 4.421679186820984, "identity": 0.5730652578175068, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.015837281197309493, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": -0.3846679701732691, "target_raw": 0.06293778195977211, "ce": 6.138576626777649, "genuineness": 4.422306728363037, "identity": 0.573683176934719, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": 0.01645520031452179, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": -0.020556643947153244, "target_raw": 0.21110441014170647, "ce": 5.8720999479293825, "genuineness": 4.444586682319641, "identity": 0.5003047451376915, "wer": 0.01625, "valid_fraction": 1, "identity_delta": -0.0569232314825058, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": -0.0468261750326548, "target_raw": 0.20041463598608972, "ce": 5.664696979522705, "genuineness": 4.377119326591492, "identity": 0.3856200444512069, "wer": 0.03267909356725146, "valid_fraction": 0.95, "identity_delta": -0.17160793216899037, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": -0.1845214813103226, "target_raw": 0.14438273645937444, "ce": 5.858746361732483, "genuineness": 4.510171389579773, "identity": 0.5630354374647141, "wer": 0.022978801169590644, "valid_fraction": 0.95, "identity_delta": 0.005807460844516754, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": -0.18657226130870402, "target_raw": 0.1435482192784548, "ce": 5.909629082679748, "genuineness": 4.583914756774902, "identity": 0.5655979804694653, "wer": 0.008680555555555556, "valid_fraction": 1, "identity_delta": 0.008370003849267959, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": -0.21079101239582415, "target_raw": 0.13369296230375766, "ce": 6.084566402435303, "genuineness": 4.549710369110107, "identity": 0.5622347168624401, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0050067402422428135, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": -0.21704101468449807, "target_raw": 0.13114966936409472, "ce": 5.987268710136414, "genuineness": 4.532137513160706, "identity": 0.5161263417452574, "wer": 0.0059649122807017545, "valid_fraction": 1, "identity_delta": -0.04110163487493992, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": -0.2266601582883502, "target_raw": 0.12723538279533386, "ce": 5.956292271614075, "genuineness": 4.546258521080017, "identity": 0.574808406829834, "wer": 0.01474673202614379, "valid_fraction": 1, "identity_delta": 0.017580430209636688, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": -0.22861328331695863, "target_raw": 0.12644060403108598, "ce": 5.809750032424927, "genuineness": 4.500757265090942, "identity": 0.5385621801018715, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.018665796518325804, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": -0.24804687497139158, "target_raw": 0.1185325562953949, "ce": 6.064511179924011, "genuineness": 4.528058040142059, "identity": 0.591836978495121, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0346090018749237, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": -0.2620117169119088, "target_raw": 0.11284988895058631, "ce": 6.065106892585755, "genuineness": 4.566028094291687, "identity": 0.5373400121927261, "wer": 0.0061111111111111106, "valid_fraction": 1, "identity_delta": -0.01988796442747116, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": -0.30541992497543796, "target_raw": 0.09518592916429043, "ce": 6.116138577461243, "genuineness": 4.529940867424012, "identity": 0.5609674736857414, "wer": 0.008680555555555556, "valid_fraction": 1, "identity_delta": 0.0037394970655441283, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": -0.31669921954388375, "target_raw": 0.09059608280658722, "ce": 6.077616620063782, "genuineness": 4.465611433982849, "identity": 0.579286377876997, "wer": 0.005756578947368421, "valid_fraction": 1, "identity_delta": 0.022058401256799698, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": -0.3292968735981872, "target_raw": 0.08546976074576378, "ce": 6.157639026641846, "genuineness": 4.539668726921081, "identity": 0.5648319281637668, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.007603951543569565, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": -0.3511718742847894, "target_raw": 0.07656823843717575, "ce": 6.10005464553833, "genuineness": 4.447410941123962, "identity": 0.54606544226408, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.011162534356117249, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": -0.3541015654895803, "target_raw": 0.07537606880068778, "ce": 6.099856114387512, "genuineness": 4.485380983352661, "identity": 0.5550859704613685, "wer": 0.01637426900584795, "valid_fraction": 1, "identity_delta": -0.0021420061588287354, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": -0.3587890690370249, "target_raw": 0.07346859835088253, "ce": 6.104423141479492, "genuineness": 4.411951208114624, "identity": 0.5534088239073753, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.0038191527128219604, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": -0.3603515632009064, "target_raw": 0.07283277772367, "ce": 6.101643204689026, "genuineness": 4.433603644371033, "identity": 0.5562194548547268, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.0010085217654705048, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": -0.3666992177129446, "target_raw": 0.07024974748492241, "ce": 6.129839706420898, "genuineness": 4.4094408512115475, "identity": 0.5662966027855874, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": 0.009068626165390014, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": -0.3880859389733338, "target_raw": 0.0615469191223383, "ce": 6.1508877038955685, "genuineness": 4.448979926109314, "identity": 0.5585209101438522, "wer": 0.005756578947368421, "valid_fraction": 1, "identity_delta": 0.0012929335236549378, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 0.2778808655508435, "target_raw": 0.3325466074049473, "ce": 5.70947380065918, "genuineness": 4.387160921096802, "identity": 0.3892023921012878, "wer": 0.0331578947368421, "valid_fraction": 0.95, "identity_delta": -0.16802558451890945, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 0.12514648428559869, "target_raw": 0.2703949064016342, "ce": 5.636847972869873, "genuineness": 4.379002106189728, "identity": 0.41637057047337295, "wer": 0.009236111111111112, "valid_fraction": 1, "identity_delta": -0.14085740614682435, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 0.012109374628090494, "target_raw": 0.22439708597958088, "ce": 5.548262405395508, "genuineness": 4.287999510765076, "identity": 0.4109220076352358, "wer": 0.07569444444444444, "valid_fraction": 0.85, "identity_delta": -0.1463059689849615, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": -0.08378906537514662, "target_raw": 0.18537344820797444, "ce": 5.686440086364746, "genuineness": 4.4301518201828, "identity": 0.46540598943829536, "wer": 0.017423245614035087, "valid_fraction": 1, "identity_delta": -0.09182198718190193, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": -0.1311035216649535, "target_raw": 0.16611993163824082, "ce": 5.67432746887207, "genuineness": 4.393750762939453, "identity": 0.4755681939423084, "wer": 0.01575657894736842, "valid_fraction": 1, "identity_delta": -0.08165978267788887, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": -0.13857422206142508, "target_raw": 0.1630799040198326, "ce": 5.670207190513611, "genuineness": 4.416030752658844, "identity": 0.4944801226258278, "wer": 0.03379751461988304, "valid_fraction": 0.9, "identity_delta": -0.06274785399436951, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": -0.24033203165767003, "target_raw": 0.12167193219065667, "ce": 6.019237995147705, "genuineness": 4.5666556596755985, "identity": 0.4977996967732906, "wer": 0.01392328861369109, "valid_fraction": 1, "identity_delta": -0.05942827984690666, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": -0.38212890800226595, "target_raw": 0.06397099420428276, "ce": 6.174715781211853, "genuineness": 4.403164863586426, "identity": 0.5572279766201973, "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": -0.416406245479869, "target_raw": 0.05002262964844704, "ce": 6.205692195892334, "genuineness": 4.336011219024658, "identity": 0.5872822225093841, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.03005424588918686, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": -0.3842773448013596, "target_raw": 0.0630967378616333, "ce": 6.181864213943482, "genuineness": 4.330990350246429, "identity": 0.5536643981933593, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.0035635784268379213, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": -0.4037109401176708, "target_raw": 0.055188688635826114, "ce": 6.19536669254303, "genuineness": 4.294589400291443, "identity": 0.578314907848835, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.021086931228637695, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": -0.37855468960271915, "target_raw": 0.06542543917894364, "ce": 6.2747140312194825, "genuineness": 4.3427893161773685, "identity": 0.5557437974214554, "wer": 0.005631469979296066, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": -0.11886718513980501, "target_raw": 0.17109922394156457, "ce": 6.067648544311523, "genuineness": 4.535463781356811, "identity": 0.5508852855861187, "wer": 0.02144739318652362, "valid_fraction": 1, "identity_delta": -0.0048585118353366855, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": -0.08798827869383732, "target_raw": 0.18366467610001563, "ce": 5.9790480422973635, "genuineness": 4.481364312171936, "identity": 0.5103233557939529, "wer": 0.01768353690550487, "valid_fraction": 0.98, "identity_delta": -0.045420441627502445, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": -0.11886718513980501, "target_raw": 0.17109922394156457, "ce": 6.067648544311523, "genuineness": 4.535463781356811, "identity": 0.5508852855861187, "wer": 0.02144739318652362, "valid_fraction": 1, "identity_delta": -0.0048585118353366855, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": 0.03087890644596771, "ci95_z": [ -0.03822265684648564, 0.11277343922508798 ], "language_deltas": { "en": -0.042187496223688024, "de": -0.03749999908453043, "fr": 0.09804688412608725, "nl": 0.16777343702796102, "es": -0.03173829361599127 }, "languages_improved": 2, "clear_gain": false, "delta_ce": -0.08860050201416016, "delta_genuineness": -0.05409946918487549, "delta_wer": -0.0037638562810187524, "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": 0.03087890644596771, "ci95_z": [ -0.03822265684648564, 0.11277343922508798 ], "language_deltas": { "en": -0.042187496223688024, "de": -0.03749999908453043, "fr": 0.09804688412608725, "nl": 0.16777343702796102, "es": -0.03173829361599127 }, "languages_improved": 2, "clear_gain": false, "delta_ce": -0.08860050201416016, "delta_genuineness": -0.05409946918487549, "delta_wer": -0.0037638562810187524, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 0.25968750446291416, "ci95_z": [ 0.18164062326632952, 0.3751562644300891 ], "language_deltas": { "en": 0.15390624822627771, "de": 0.21835938515599052, "fr": 0.24804687314045246, "nl": 0.19843749851236195, "es": 0.4796875172794881 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.20706548690795898, "delta_genuineness": 0.19267446517944337, "delta_wer": 0.015815923207227554, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 3.0, "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain" }, "reference_only": true, "updated": 1793024564.6611812, "example": { "text": "Quelqu’un a déplacé la petite chaise bleue. Elle était ici... près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "sentences": [ "Quelqu’un a déplacé la petite chaise bleue.", "Elle était ici... près de la grande bibliothèque.", "Nous la remettrons après le déjeuner." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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.", "language": "fr", "seed": 1701, "scale": 0.0, "cfg": 3.0, "frames": 128, "reference": true } }, "rows": [ { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "005ffe95110816d8800e42e3e7db9d5a7b9e39a2bbca89c36ca3052f4f09cd00", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "be042164945e1ac0b5d31b32d1dd1b3215769967107ecdc6dd8070cbfbb5b13d", "generation_seconds_batch": 24.326306545059197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021569550037384033, "target_z": -0.4863281211378628, "ce": 6.356205940246582, "genuineness": 4.469690799713135, "identity": 0.3704555928707123, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/005ffe95110816d8800e42e3e7db9d5a7b9e39a2bbca89c36ca3052f4f09cd00.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": "008febf71275eeb1178d35c2846d8bd85ccec205f9b69987bdc55fdbf3248378", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Your message arrived after I had left.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8cecc0d7dac946638fbd10a2178a2c9f48d0a60901f6204609dd949f4f641346", "generation_seconds_batch": 23.630005580955185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10025264322757721, "target_z": -0.2929687542912636, "ce": 6.2767791748046875, "genuineness": 4.293961524963379, "identity": 0.30089354515075684, "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_Bitterness/008febf71275eeb1178d35c2846d8bd85ccec205f9b69987bdc55fdbf3248378.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "0179094a0b9fb312d659171e39a472d637cc5fa15c09adedaa81dd4fa9947f04", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e3d64ec3dd48e45d991dd4ac96d2272e49192ccdb6e01ce587f3e946c714df6a", "generation_seconds_batch": 19.36377520102542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07799884676933289, "target_z": -0.34765623312102983, "ce": 6.109982967376709, "genuineness": 4.645420074462891, "identity": 0.5634023547172546, "hypothesis": "La porte 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_Bitterness/0179094a0b9fb312d659171e39a472d637cc5fa15c09adedaa81dd4fa9947f04.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": "018d374e2ce040f30f5cc62284faeef683415bf2d87687649f2b5b79729a85fe", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0207af7c044f3f328aa596b504d02adcf2ce0c6f9c5938efa70ec2a95facce0f", "generation_seconds_batch": 15.825979516957887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13283857703208923, "target_z": -0.2128906171326834, "ce": 6.165581703186035, "genuineness": 4.432034492492676, "identity": 0.6430240869522095, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était qu'ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/018d374e2ce040f30f5cc62284faeef683415bf2d87687649f2b5b79729a85fe.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "01a1982631509eee471ac19eaca1968e4309919ad056bd059a45229045a5e927", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "cc1a0bb1e68ddc82d2774893ef16288557841385252e2f9ce5386b007bf12b21", "generation_seconds_batch": 24.478706346009858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10025264322757721, "target_z": -0.2929687542912636, "ce": 6.0146708488464355, "genuineness": 4.632867813110352, "identity": 0.5349265933036804, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/01a1982631509eee471ac19eaca1968e4309919ad056bd059a45229045a5e927.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "11276b0e1634a95f0a40f9fa6e94e9bdcbfa13aec18018da2e13fb9efd78cccf", "generation_seconds_batch": 17.207908757962286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009426817297935486, "target_z": -0.5624999862679565, "ce": 6.2767791748046875, "genuineness": 4.457139015197754, "identity": 0.8176884651184082, "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_Bitterness/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "029cf99f5a0f8c260cb377c202e5789e1e7ea877099d5a13072c566f0aeb4c66", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a86ae0beca8dbc44b1d03e3b3a78e2feade66013d96483245bcbd44099e072b3", "generation_seconds_batch": 21.998680577031337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15986105799674988, "target_z": -0.14648435883624045, "ce": 5.863759994506836, "genuineness": 4.124508857727051, "identity": 0.47326093912124634, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/029cf99f5a0f8c260cb377c202e5789e1e7ea877099d5a13072c566f0aeb4c66.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "02c2368bce5f6d1e1c4c210c24f9f859ee315acad2ad3378331ae3d6468e8e7f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "089e82e860ba7c686448e9fad773deabf3896e3f9e4dcdbd36db586e5c300a93", "generation_seconds_batch": 19.13791134406347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10820043087005615, "target_z": -0.27343750400517935, "ce": 6.062326908111572, "genuineness": 4.557555198669434, "identity": 0.6517285108566284, "hypothesis": "De deur 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_Bitterness/02c2368bce5f6d1e1c4c210c24f9f859ee315acad2ad3378331ae3d6468e8e7f.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "0347751780e944fff69c0ca1eca3f256c24e79a8a7f16bac17ffb3d83808efc5", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1b043e18a8fa05d830080b8edabd71ee18d51b80f93eccf50fae71c58eae2862", "generation_seconds_batch": 22.826042141998187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12409600615501404, "target_z": -0.23437500343301088, "ce": 6.054384231567383, "genuineness": 4.444586753845215, "identity": 0.603171706199646, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/0347751780e944fff69c0ca1eca3f256c24e79a8a7f16bac17ffb3d83808efc5.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "038f3363d640ee9a6afbeca2302b95cb85411159574bacffc0ada8bacb37dfb7", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6e9d56bf78f564e582e01a0fe2cfdb8acb87b3ff77c83c9b4d0cd9d8c7cf965b", "generation_seconds_batch": 25.801949035958387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1089952141046524, "target_z": -0.2714843679909361, "ce": 6.054384231567383, "genuineness": 4.720732688903809, "identity": 0.8056541085243225, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/038f3363d640ee9a6afbeca2302b95cb85411159574bacffc0ada8bacb37dfb7.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "03b73304bb0fce1cbb7718b87a6a48dfdaac093f59454492d3482ebb0ce9de50", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "059b16f14faacd36276cb53a81484e1616a9f0eb32e2ef77cb075d6cca62a19b", "generation_seconds_batch": 22.96614741103258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2790778577327728, "target_z": 0.14648435883624045, "ce": 5.383228778839111, "genuineness": 4.381826400756836, "identity": 0.40327388048171997, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/03b73304bb0fce1cbb7718b87a6a48dfdaac093f59454492d3482ebb0ce9de50.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "03c97ace18cbcac7150d80fa6de23b1cf57f0e565cc56da06b93b5ff9e61b74f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "74145751a7377ef720a2aecc4d2ca5fb1ba5998ea68f0a8ddb4207c2154f89b6", "generation_seconds_batch": 24.373580323066562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0986630842089653, "target_z": -0.2968750080103587, "ce": 6.141753673553467, "genuineness": 4.532451152801514, "identity": 0.5113112926483154, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/03c97ace18cbcac7150d80fa6de23b1cf57f0e565cc56da06b93b5ff9e61b74f.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "042276d63cea53a5fe4d653dfde2b98131a47a6268e31a22403e3b1fd57c3965", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "17db923e9ead0cb4255a97e99722b2100620407619266a4cd43b07a66dacfa3c", "generation_seconds_batch": 16.8462101490004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10263697803020477, "target_z": -0.2871093828673166, "ce": 6.213237762451172, "genuineness": 4.469690799713135, "identity": 0.3206616938114166, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/042276d63cea53a5fe4d653dfde2b98131a47a6268e31a22403e3b1fd57c3965.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "048d613011d756625c76193148f51ac4ea0e7dfb1386d48a29d028edf2d07c3e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "78e94ac00299324490be92d080b873c09ad7bcdb1558ce8deb0bfeed7cefc1b1", "generation_seconds_batch": 24.625534544000402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06607715785503387, "target_z": -0.37695312685954757, "ce": 5.748591423034668, "genuineness": 4.331617832183838, "identity": 0.7104122638702393, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/048d613011d756625c76193148f51ac4ea0e7dfb1386d48a29d028edf2d07c3e.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "0548308d0cd2e38f052f5a9028d6ad23d734e78599e8042ca6798ce1b6f5a8aa", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "42cb4fc5102f676e3a95fb246cb529e5f04cffdb8dcda9fbfa953a388408f2da", "generation_seconds_batch": 22.72239885595627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05812937021255493, "target_z": -0.3964843771456318, "ce": 5.959072113037109, "genuineness": 4.337893962860107, "identity": 0.8033362627029419, "hypothesis": "La porte 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_Bitterness/0548308d0cd2e38f052f5a9028d6ad23d734e78599e8042ca6798ce1b6f5a8aa.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "01515cd3956169dd78b2282ec2710ad8b15984d5a2fc91aa28916694ef4aa717", "generation_seconds_batch": 16.97746044700034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06687194108963013, "target_z": -0.37499999084530433, "ce": 6.403861999511719, "genuineness": 4.758388519287109, "identity": 0.6556930541992188, "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_Bitterness/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "05deb5b369b5da23cf4c1e83334107458d4c15092410076a6e72d4dbfe0dca2a", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "744b80a643ec7cdee101b4e678e5c65504411619d0a6a16c219955853b560580", "generation_seconds_batch": 18.491830673068762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07879361510276794, "target_z": -0.3457031337255693, "ce": 6.022613525390625, "genuineness": 4.331617832183838, "identity": 0.7328541278839111, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/05deb5b369b5da23cf4c1e83334107458d4c15092410076a6e72d4dbfe0dca2a.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "0675dbc384571f38ee54dc0e54f46c9da6df2c9420f14f340ae00f4d7d4845ff", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "718a876bb46f2d460ec739898713ffe4429afe31ad1958074e640d57c5bfed7b", "generation_seconds_batch": 23.842542489990592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10343176126480103, "target_z": -0.28515624685307334, "ce": 6.205295085906982, "genuineness": 4.65797233581543, "identity": 0.7696284651756287, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/0675dbc384571f38ee54dc0e54f46c9da6df2c9420f14f340ae00f4d7d4845ff.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "071e5833eaa68eecbe31483ab02042faa1da232c99bdce33b1f5629f4a200dd4", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e5191382a628c7ef98fd1db3908fa4af250ef8945f5fa2389175cb8214cf2513", "generation_seconds_batch": 24.23628716391977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006247714161872864, "target_z": -0.554687515448549, "ce": 6.324435234069824, "genuineness": 4.268857479095459, "identity": 0.443639874458313, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/071e5833eaa68eecbe31483ab02042faa1da232c99bdce33b1f5629f4a200dd4.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "07876dbebca52038dd2606aec353776242152a9587acf67bbec4788cb5b190eb", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "da3b121af4988dd7596eec2db83fcbec795a001817a686c8eb31772cc35ac34b", "generation_seconds_batch": 19.954143104027025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08276751637458801, "target_z": -0.33593749027313585, "ce": 6.205295085906982, "genuineness": 4.6203155517578125, "identity": 0.7214640378952026, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/07876dbebca52038dd2606aec353776242152a9587acf67bbec4788cb5b190eb.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "078c976cab6564514d8673a97823d90f8aa593b7e859acbbd6b5a216638bba23", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "6bd9244eb67a78f4945da8cdb0be1644c02773034cdd76ce01e514700827ca4b", "generation_seconds_batch": 15.50353637104854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.020553722977638245, "target_z": -0.5898437439922309, "ce": 6.41180419921875, "genuineness": 4.262581825256348, "identity": 0.4501188099384308, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/078c976cab6564514d8673a97823d90f8aa593b7e859acbbd6b5a216638bba23.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "078dc2719e61f20d2b5af0ee86454797d87ba20a79637ac14c6101bca63eac23", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8526ad99d513caea43f2ed671c530931d52c5c66acee8a3bacb20f55f1634e12", "generation_seconds_batch": 23.350299171055667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16621927917003632, "target_z": -0.1308593805786427, "ce": 5.903473377227783, "genuineness": 4.356721878051758, "identity": 0.33877822756767273, "hypothesis": "Ik heb een klein doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/078dc2719e61f20d2b5af0ee86454797d87ba20a79637ac14c6101bca63eac23.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "07c6e8f758495d85a1a915af99f7f391d6f6412dff2442287217aeb7934025db", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "478b37efda6f3ef1ceb3443fb09ec3f37f268d9f6f1f3de2f0711c17bce3506f", "generation_seconds_batch": 21.897297795978375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1805253028869629, "target_z": -0.09570311541617796, "ce": 5.363371849060059, "genuineness": 4.532451152801514, "identity": 0.5768178701400757, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/07c6e8f758495d85a1a915af99f7f391d6f6412dff2442287217aeb7934025db.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "083cfcdbe207957b072b85172ab9640e2824c97dc41414ef9debf73979d31f0c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8872724e3e38d32fa19d18fa22310eef49351a6259c286d24ae59d73d18f25e8", "generation_seconds_batch": 16.852264299057424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11932733654975891, "target_z": -0.24609374628090488, "ce": 6.24500846862793, "genuineness": 4.65797233581543, "identity": 0.6525954008102417, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/083cfcdbe207957b072b85172ab9640e2824c97dc41414ef9debf73979d31f0c.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "088b3070c027f009e28653140d566a43b401cf852a206498ee07e3b64d740313", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1b1d0fba4a1c6cee21ad69fb32d4dea28860bd2d9a42dd0c1057f60ad5cbe2a7", "generation_seconds_batch": 21.68685894506052, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20516343414783478, "target_z": -0.03515626516246472, "ce": 6.109982967376709, "genuineness": 4.758388519287109, "identity": 0.6449013948440552, "hypothesis": "La porte 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_Bitterness/088b3070c027f009e28653140d566a43b401cf852a206498ee07e3b64d740313.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "08d55cc6488d932c0a216fe6743774097162dd673644c7d1a1774e0591ee9025", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8721e08740d7bbfeb4d02ecfe801390b70e1b350d8aacb3822156748f93fc8fb", "generation_seconds_batch": 22.400180338998325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08435706794261932, "target_z": -0.3320312548634321, "ce": 6.173524379730225, "genuineness": 4.557555198669434, "identity": 0.3921807110309601, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/08d55cc6488d932c0a216fe6743774097162dd673644c7d1a1774e0591ee9025.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "08dc9692271db0158bca0f0b86c45528f861e6583eb4bcbdf33c0a8185961631", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "be606f1ff913e96ff6eba172397c57336f12ec23c710f62d75a4aa181ceb6bae", "generation_seconds_batch": 22.72239885595627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08594663441181183, "target_z": -0.3281249828349456, "ce": 6.197352409362793, "genuineness": 4.68307638168335, "identity": 0.7455548644065857, "hypothesis": "La porte 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_Bitterness/08dc9692271db0158bca0f0b86c45528f861e6583eb4bcbdf33c0a8185961631.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "0987ad397f3be7e308264997515e15ffac863a91baf43523d179582f8b5baea5", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b7c5d821dfa20a0e2e43f2d93246e81e973032df4c6d13057deb42b048d451b8", "generation_seconds_batch": 23.148368171066977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035875558853149414, "target_z": -0.4511718925941808, "ce": 6.332377910614014, "genuineness": 4.337893962860107, "identity": 0.23084385693073273, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/0987ad397f3be7e308264997515e15ffac863a91baf43523d179582f8b5baea5.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": "09eeaf302c0822f830e3f9d400fdff9c29e1c088c0ebc6ccd962d917d3e6e5f7", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6bb5477fce17704a20fa31140b3a47ed135916ab48a13027252d0a00f264d504", "generation_seconds_batch": 24.66101698903367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19562609493732452, "target_z": -0.05859375085825272, "ce": 5.371314525604248, "genuineness": 4.507347106933594, "identity": 0.7141244411468506, "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_Bitterness/09eeaf302c0822f830e3f9d400fdff9c29e1c088c0ebc6ccd962d917d3e6e5f7.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "0b3c2bd0ffea4c2efbbfe0a185dc38b0799ef052dfabea6953ad0f5b939cab7c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2ce88097876fabe15936872070c3a0d3619e49d5cdde79bd18386611a7bcae56", "generation_seconds_batch": 23.471891490044072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09627874940633774, "target_z": -0.3027343794343057, "ce": 6.078212261199951, "genuineness": 4.319066047668457, "identity": 0.304240882396698, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/0b3c2bd0ffea4c2efbbfe0a185dc38b0799ef052dfabea6953ad0f5b939cab7c.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "0bb917a16d21b2672c1abe8b258337e6d8b6196c2dfb9a46d5bfb75f193ff9a4", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b5ddebbaf36533fb6781a9bea6f55b2b4f94783c932a4e5a25b383bc19779ae9", "generation_seconds_batch": 24.008186280960217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03269645571708679, "target_z": -0.4589843634135883, "ce": 6.125868320465088, "genuineness": 4.570107460021973, "identity": 0.39836227893829346, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/0bb917a16d21b2672c1abe8b258337e6d8b6196c2dfb9a46d5bfb75f193ff9a4.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "0bdc5fb9b5a7b9acbebcacf5f1a6a988db0ce9acd13a6fe99d51a2b64e72779e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "955a2e477a2046104dbd3300df274903decc78afe6eaacdde2f56c6252b14ecf", "generation_seconds_batch": 23.23725445510354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14317069947719574, "target_z": -0.18749999542265217, "ce": 6.070269584655762, "genuineness": 4.808597087860107, "identity": 0.5312443375587463, "hypothesis": "La porte 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_Bitterness/0bdc5fb9b5a7b9acbebcacf5f1a6a988db0ce9acd13a6fe99d51a2b64e72779e.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "0be8492799aab11a355edf48908be7fdfea05137680937d1b18fb867c9615fb3", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3057e1a1b48ca9f62ec35219cbd82be58d5f03be4dbb33c357551049238559f1", "generation_seconds_batch": 23.971329362946562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.510358452796936, "target_z": 0.7148436799093612, "ce": 5.911416053771973, "genuineness": 4.124508857727051, "identity": 0.21823623776435852, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/0be8492799aab11a355edf48908be7fdfea05137680937d1b18fb867c9615fb3.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "0c05e5fce6ae0864f89c1cca20b0d3598fd4b723a8dda19032bcd51ae20fbd0b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4524b644353be90fddf8ada58badc380203d6984c51c40aa8d700ffc4b2f5fd7", "generation_seconds_batch": 29.362718177959323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2202642410993576, "target_z": 0.001953136014243242, "ce": 5.967014789581299, "genuineness": 4.7332844734191895, "identity": 0.674897313117981, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/0c05e5fce6ae0864f89c1cca20b0d3598fd4b723a8dda19032bcd51ae20fbd0b.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "0c55b49459363a261d963ce74a12a0888bc0720a7f1f2b56c4257f528a9b0429", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "edcef1204cf3f3684973ae86aa2c2ad7b68725faf206f802de8a068b69bfe05e", "generation_seconds_batch": 21.086783951963298, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1980104297399521, "target_z": -0.05273437943430572, "ce": 5.756534099578857, "genuineness": 4.632867813110352, "identity": 0.5388445258140564, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/0c55b49459363a261d963ce74a12a0888bc0720a7f1f2b56c4257f528a9b0429.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "0c66c22bb8761df3fe28cf97e23b3ec756281c19abdd69f9b300e0f9e905cb67", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "717deebcc0a9b39a7456ff4357b1b8c0ce7200538e39e016b7a45d742e2e1511", "generation_seconds_batch": 22.701002361020073, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014416545629501343, "target_z": -0.5039062354097038, "ce": 5.974957466125488, "genuineness": 4.6705241203308105, "identity": 0.5429380536079407, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/0c66c22bb8761df3fe28cf97e23b3ec756281c19abdd69f9b300e0f9e905cb67.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "0c968e95f3111f33e6623c46b22431a23d902a9994eefc2e27d4aca38c2846a4", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d57e9f2d7807534516683a93214ad34629715d444e33dc454cda7dea173c74e9", "generation_seconds_batch": 22.697491565020755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12091689556837082, "target_z": -0.24218749256180977, "ce": 6.141753673553467, "genuineness": 4.846253395080566, "identity": 0.8644725680351257, "hypothesis": "La porte 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_Bitterness/0c968e95f3111f33e6623c46b22431a23d902a9994eefc2e27d4aca38c2846a4.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "3cd560036210c75184100fbc7c46ccd83509ba36370b4513e90affde74323f98", "generation_seconds_batch": 17.516566104022786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023159101605415344, "target_z": -0.48242188572815903, "ce": 6.324435234069824, "genuineness": 4.15588903427124, "identity": 0.7333153486251831, "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_Bitterness/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.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": "0ce4a6e1c4ba1c3ccc7b93052158288a3e6183816b7df0a55b1cf15ebf0e8406", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2f9bfc8852d96d0d9b76e28bb1f1a916901303b5034127620acc5b9a38f69e26", "generation_seconds_batch": 23.938470973982476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17655140161514282, "target_z": -0.10546875886861144, "ce": 5.911416053771973, "genuineness": 4.6705241203308105, "identity": 0.6234462857246399, "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_Bitterness/0ce4a6e1c4ba1c3ccc7b93052158288a3e6183816b7df0a55b1cf15ebf0e8406.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "0d496157e14d16ad1ebba7f0c5f197a34d300b874fcdef43da299a9695c4aa03", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "890834d6fd6fc2983aa69b594625bc46c7ad85954fe82cc3be5ff412663c63a5", "generation_seconds_batch": 23.315498390002176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11694300174713135, "target_z": -0.2519531177048519, "ce": 5.895530700683594, "genuineness": 4.6956281661987305, "identity": 0.5949388742446899, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/0d496157e14d16ad1ebba7f0c5f197a34d300b874fcdef43da299a9695c4aa03.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "0d67dccd96bbff6a5feabaa35829939b5a53a6ce097ba65b1820df62fef6e6eb", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "38e9b3791a7077757b45384f5da3fd1b1b69b33ca3e0d9a2c3488d8b5c39506c", "generation_seconds_batch": 22.243028830038384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14714458584785461, "target_z": -0.1777343885890014, "ce": 6.133810997009277, "genuineness": 4.582659721374512, "identity": 0.38951194286346436, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/0d67dccd96bbff6a5feabaa35829939b5a53a6ce097ba65b1820df62fef6e6eb.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": "0d771e84e35b9a21de793b9fd7e5f4bbc6a2b3b76c0f0a2a7c04706e14192076", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The keys are on the kitchen table.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c0d0232d277810d2e183edde59d2dc25b44b9c2f02498540c0b7db0a221cb4b", "generation_seconds_batch": 18.448489908943884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029517337679862976, "target_z": -0.4667968708517785, "ce": 6.324435234069824, "genuineness": 4.243753433227539, "identity": 0.33709535002708435, "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_Bitterness/0d771e84e35b9a21de793b9fd7e5f4bbc6a2b3b76c0f0a2a7c04706e14192076.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "0e09d906ac3a886a151c903a443cb726a7475cfe66daca2f62ec6d40c942cad2", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c5d0ce1f3f4913155a8939e5ff285f03833aa3eda9d111ffc0211573f4eab838", "generation_seconds_batch": 18.166900111944415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15350282192230225, "target_z": -0.1621093737126209, "ce": 5.990842819213867, "genuineness": 4.061748504638672, "identity": 0.4305846691131592, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/0e09d906ac3a886a151c903a443cb726a7475cfe66daca2f62ec6d40c942cad2.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": "0e71fb317ad06120d8c164e296a05f526e6841c706868797ae1e1c460b03cd12", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "016e74d4391fdff9a1be4f8bcca0d52e3c1a9cb354ae283df203db6549dddf6e", "generation_seconds_batch": 22.26077409205027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2099321186542511, "target_z": -0.023437485695787998, "ce": 6.1020402908325195, "genuineness": 4.607763767242432, "identity": 0.47891929745674133, "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_Bitterness/0e71fb317ad06120d8c164e296a05f526e6841c706868797ae1e1c460b03cd12.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "0e9bd7fbea3adc70ef29f8f519505c3d26938dcee1d24a8bb1bb28ff6d4fd404", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9d7e1a6af5aa39764c0bdb67316dbda2568429a95ccaa6b5bcf839f52d37b0e8", "generation_seconds_batch": 24.930891500087455, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008058309555053711, "target_z": -0.5195312502860843, "ce": 6.38797664642334, "genuineness": 4.3881025314331055, "identity": 0.3836594223976135, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/0e9bd7fbea3adc70ef29f8f519505c3d26938dcee1d24a8bb1bb28ff6d4fd404.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "0f5ee98230faa486204806f0b288ead9fea070d1880e1a13bf813bec5f929d4b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a61c967db47da745a847d3c987065843a4bdea3dad1291f60e5a70d1e6c69fcd", "generation_seconds_batch": 17.45161718199961, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1455550342798233, "target_z": -0.18164062399870515, "ce": 5.935244083404541, "genuineness": 4.557555198669434, "identity": 0.4217855930328369, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/0f5ee98230faa486204806f0b288ead9fea070d1880e1a13bf813bec5f929d4b.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "0fa0056d199ef624f146afc064725cf3426d281916653bc5b49900307518c1a5", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "960cf0a6329200ed9090dfafbf6dbd760f7a8fd57c0ea7cd387decc3394479d6", "generation_seconds_batch": 21.72680138493888, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21390600502490997, "target_z": -0.01367187886213724, "ce": 5.085378646850586, "genuineness": 4.3881025314331055, "identity": 0.5762406587600708, "hypothesis": "La puerta sigue abierta y dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/0fa0056d199ef624f146afc064725cf3426d281916653bc5b49900307518c1a5.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "0fe6a18a77cf7ffdff3ca0fc6cedda5abba69f6b9b03392168c54b9ddad5b6af", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7d2e9a479d083c61158b1a55add94789d731c029f6e596dbe262707a3ca622b4", "generation_seconds_batch": 22.43190692400094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03746512532234192, "target_z": -0.4472656205656943, "ce": 6.229123115539551, "genuineness": 4.030367851257324, "identity": 0.3871982991695404, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/0fe6a18a77cf7ffdff3ca0fc6cedda5abba69f6b9b03392168c54b9ddad5b6af.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "1029fd3bbdec7b1f9a474f2d9aa790a75be2a8ba8fecfbc24f7f6107990cdc52", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3e1ec39bf7df7c8d14b76a6507dc27420aa370020b7e2ecc83e1ffc4d0d6e098", "generation_seconds_batch": 17.269432975910604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09548397362232208, "target_z": -0.3046874971391576, "ce": 6.197352409362793, "genuineness": 4.13078498840332, "identity": 0.1540052443742752, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/1029fd3bbdec7b1f9a474f2d9aa790a75be2a8ba8fecfbc24f7f6107990cdc52.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "1040d8880f21268d4121a04ede87d7acf2109ef80e7afcc802af0a236062a9d8", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1fd93364001da8d3515cc516277457e870cfb4a2e892a92bb9c163407651b227", "generation_seconds_batch": 24.40575316408649, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06130848824977875, "target_z": -0.38867186970744155, "ce": 6.229123115539551, "genuineness": 4.457139015197754, "identity": 0.19674457609653473, "hypothesis": "The door is still open. Like put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/1040d8880f21268d4121a04ede87d7acf2109ef80e7afcc802af0a236062a9d8.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "10b36887e43f9ffb8c4c630ffc4b91e4ef8891c24289e4ffd773bb0619c215db", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "22455f480bfd3418d615759b1f18c1d2af73ccd161710a0cd67c8850d4203d21", "generation_seconds_batch": 29.362718177959323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19006264209747314, "target_z": -0.07226562972038995, "ce": 6.0146708488464355, "genuineness": 4.582659721374512, "identity": 0.5512031316757202, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/10b36887e43f9ffb8c4c630ffc4b91e4ef8891c24289e4ffd773bb0619c215db.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "110ce68f606d5ae966881bf4b527546a36bdb88fbbe801fe49bd2e33c11a734e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e04fea0f59d0e02a49e114676575b31f7987a9537a09aa6a15b5411f1a55fa4a", "generation_seconds_batch": 26.771555451094173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11853255331516266, "target_z": -0.24804688229514812, "ce": 6.133810997009277, "genuineness": 4.400654315948486, "identity": 0.5458619594573975, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/110ce68f606d5ae966881bf4b527546a36bdb88fbbe801fe49bd2e33c11a734e.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "1159ae3cf4ea12606233adda75916eb96a7d4ad08b685ad5c88e56082aadf57c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8097286d6c051b4783d4fb7038d35db8ca846c5a982b8169af0686881763f26e", "generation_seconds_batch": 24.980551181011833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003068596124649048, "target_z": -0.5468750080103587, "ce": 6.24500846862793, "genuineness": 4.532451152801514, "identity": 0.4513528048992157, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/1159ae3cf4ea12606233adda75916eb96a7d4ad08b685ad5c88e56082aadf57c.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "116f2db8115fd8abf6cc01dab217b050ffe435bb4e92632c1c8361d04213f094", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "03565b8f1385cbdd5f9a1f360ff82d66aefb135e7dd86eb6b8de35161fcd8197", "generation_seconds_batch": 21.57100839400664, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09786830842494965, "target_z": -0.2988281257152106, "ce": 4.961274147033691, "genuineness": 4.2751336097717285, "identity": 0.45185279846191406, "hypothesis": "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_Bitterness/116f2db8115fd8abf6cc01dab217b050ffe435bb4e92632c1c8361d04213f094.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "118449cb23afd8285ebf0f280491bd264ddeab3c00e7d72b747cf8fcaa3f8422", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "31b506b8229ad722fa84d817c2ee2bf0e319956d5ffd1ec0e9f0af97b094ab33", "generation_seconds_batch": 25.025806077057496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08356228470802307, "target_z": -0.33398439087767534, "ce": 6.252951145172119, "genuineness": 4.319066047668457, "identity": 0.21281243860721588, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/118449cb23afd8285ebf0f280491bd264ddeab3c00e7d72b747cf8fcaa3f8422.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "11c2ce234541a7c38bf51f80758a7e432d2523a2d554772e03b74c6dbd55408d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d6165728a9ff27caf9c53b0ea9425901bdb6521bbe0b895e45588159840a80a2", "generation_seconds_batch": 22.663737167953514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20675300061702728, "target_z": -0.03124999313397824, "ce": 5.784333229064941, "genuineness": 4.632867813110352, "identity": 0.4862699508666992, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/11c2ce234541a7c38bf51f80758a7e432d2523a2d554772e03b74c6dbd55408d.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "1238f5e805c7daf5f4f2a9a0cc74b20eddb98f3cd2f26c47b70e755c225c2488", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a50fd11250fba33479523b2cf1212e482e221e45d501c7e578a42a9b88bd7624", "generation_seconds_batch": 22.881412907969207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09071530401706696, "target_z": -0.3164062399870516, "ce": 5.824047088623047, "genuineness": 4.68307638168335, "identity": 0.8229218125343323, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/1238f5e805c7daf5f4f2a9a0cc74b20eddb98f3cd2f26c47b70e755c225c2488.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "3aa5dd874ab98959581a2c1a4804d1c1cefe3bab6767b8ec8968658407cd55f4", "generation_seconds_batch": 18.97841065202374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0342860072851181, "target_z": -0.45507812800388453, "ce": 6.403861999511719, "genuineness": 4.1998209953308105, "identity": 0.5164222121238708, "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_Bitterness/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.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": "12cbf28e6594423684885e014327925941d476a0e69f50f8e85133700c20e1e3", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The road turns left behind the bridge.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f000546f0b4988e7ee5d5de9d028285ddce3c58cd8ff5b227d11c1099365480c", "generation_seconds_batch": 17.491377745987847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12965945899486542, "target_z": -0.22070312457087363, "ce": 6.324435234069824, "genuineness": 4.068024158477783, "identity": 0.2790113389492035, "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_Bitterness/12cbf28e6594423684885e014327925941d476a0e69f50f8e85133700c20e1e3.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "12fcbfeec089000231cd969ac3dfc227354b091e82e8217969f0b851efeff449", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d8ecb7495cb0249243716efd7a50ed7dd8e7bcef27172c2f44c1160c689bc3a2", "generation_seconds_batch": 17.78396177093964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12330123037099838, "target_z": -0.23632812113786275, "ce": 5.752562999725342, "genuineness": 4.808597087860107, "identity": 0.6235084533691406, "hypothesis": "La porte 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_Bitterness/12fcbfeec089000231cd969ac3dfc227354b091e82e8217969f0b851efeff449.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "131b395fd269ce52faf6a97884c3c201052b452556f500e35349ed3141fd8f67", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "83e67ee73c5e4615f2d48927e77026673b87d350c780d8a7b9e543e56cb4ae7a", "generation_seconds_batch": 16.024652096093632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08197273313999176, "target_z": -0.3378906262873791, "ce": 5.919358730316162, "genuineness": 4.293961524963379, "identity": 0.5083385109901428, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/131b395fd269ce52faf6a97884c3c201052b452556f500e35349ed3141fd8f67.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "1345ab782bfcd1630158d0fa40dd7b92480996f6d42a3e756889f204de8eeae2", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3583f1326f6f7ccd2984fb19876b8bc24dea95143d49fa61427ae2a9bd1194dc", "generation_seconds_batch": 24.245086793904193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07561449706554413, "target_z": -0.35351564116375955, "ce": 6.0305562019348145, "genuineness": 4.871357440948486, "identity": 0.7354735136032104, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/1345ab782bfcd1630158d0fa40dd7b92480996f6d42a3e756889f204de8eeae2.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "134613ad00dd3c5267e1e54add914d480085e51538ecd88c3d3db134e7174271", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "41e0054a7320b3d83538a9beba08cbd8de885e08cde68edae59de20c78d7fb39", "generation_seconds_batch": 24.326306545059197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.014195501804351807, "target_z": -0.5742187657346332, "ce": 6.348263263702393, "genuineness": 4.419482707977295, "identity": 0.5348669290542603, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/134613ad00dd3c5267e1e54add914d480085e51538ecd88c3d3db134e7174271.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "138c9bad34eafc0de1479b1be1312ba2efb48c91d5f9a62bd048c1b65f83e174", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "94e2c0eea68f3a88ef2445f18127f1894db92c169f801dfcdbae1e5e7f4d3222", "generation_seconds_batch": 22.12626471905969, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.036449313163757324, "target_z": -0.6289062811831821, "ce": 6.2767791748046875, "genuineness": 4.532451152801514, "identity": 0.5125761032104492, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/138c9bad34eafc0de1479b1be1312ba2efb48c91d5f9a62bd048c1b65f83e174.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": "13b80392a05d8b9e724f912ff94c32fde14769a2d02e1fbe4f966e7e9b494e98", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Your message arrived after I had left.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "814f30467442d644b27e8fba1306b7b3d432a8ed92f2d363d2899f2b892f8b25", "generation_seconds_batch": 18.293989134021103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13840201497077942, "target_z": -0.19921877488932888, "ce": 6.348263263702393, "genuineness": 4.532451152801514, "identity": 0.31213653087615967, "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_Bitterness/13b80392a05d8b9e724f912ff94c32fde14769a2d02e1fbe4f966e7e9b494e98.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "13c143032a9f08867bc4b0f3fb83304a4dcfb7446939860041d5ee94f44d854c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "be5b224f331e3ba43eaab596ba4367182effca78d3262bf7919c1767ee8ecdb9", "generation_seconds_batch": 22.625727439997718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14078636467456818, "target_z": -0.19335936684659916, "ce": 4.94737434387207, "genuineness": 4.168440818786621, "identity": 0.7835485935211182, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/13c143032a9f08867bc4b0f3fb83304a4dcfb7446939860041d5ee94f44d854c.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "140335fcd0f20f7c4f8a40a4928e2cd4eb83c7f2098a1ca0e5d5563664095345", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9e9eb9a2f19614d16c86914ad080497dc9a0f28ace7059a25e1337af98ebe7d8", "generation_seconds_batch": 24.363633590051904, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16065582633018494, "target_z": -0.1445312594407799, "ce": 5.732706069946289, "genuineness": 4.557555198669434, "identity": 0.1017615795135498, "hypothesis": "La porte corps ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "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_Bitterness/140335fcd0f20f7c4f8a40a4928e2cd4eb83c7f2098a1ca0e5d5563664095345.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "1436ef4f171d2557a73703b3eb4951d8413f9cfd65182a7e22e507d6269d3ab4", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2f623787a829738232bb45b3ef4332c2038721fd88b035bdc3d03a322fcccdf4", "generation_seconds_batch": 23.68796982697677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12330123037099838, "target_z": -0.23632812113786275, "ce": 5.2045183181762695, "genuineness": 4.519899368286133, "identity": 0.6225738525390625, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/1436ef4f171d2557a73703b3eb4951d8413f9cfd65182a7e22e507d6269d3ab4.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "147887856f4eb0b2f7d18aebc1099fbae8e0dec0d964b20835f1f41c07a265cd", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "81f8236d0c7eeaecebf9ca55691ffabc4e12b8498b387afc98e315ce33b198c1", "generation_seconds_batch": 21.357082108035684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20436866581439972, "target_z": -0.03710936455792524, "ce": 5.998785495758057, "genuineness": 4.645420074462891, "identity": 0.7432037591934204, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/147887856f4eb0b2f7d18aebc1099fbae8e0dec0d964b20835f1f41c07a265cd.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "14f78ad6236b8bd925c8e0a9973fb97efc6032d052d1b4e079ea3c9f1ac391a4", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4a625e62395eae0dc51e7ce3ee391ae7e3909bee7077c6050dcaae0c071a6bd", "generation_seconds_batch": 22.380768028087914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10104742646217346, "target_z": -0.2910156182770204, "ce": 6.300607204437256, "genuineness": 4.306513786315918, "identity": 0.344326913356781, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/14f78ad6236b8bd925c8e0a9973fb97efc6032d052d1b4e079ea3c9f1ac391a4.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "389dfaf152bb262fdd05f26ee4c00cae477d225705a70e360ef641e1ea62196b", "generation_seconds_batch": 17.782095110975206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054950252175331116, "target_z": -0.404296884583822, "ce": 6.332377910614014, "genuineness": 4.193545341491699, "identity": 0.6065137386322021, "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_Bitterness/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "15657882f58ea32dc4994f0ae14d6ea7bbc853e73cd64234e35258fad7c5a009", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4a83fd2b13b2a6c5c27342008ea28ed5baa7d5195661f0311f42a425d39393b1", "generation_seconds_batch": 15.09683582407888, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03190167248249054, "target_z": -0.4609374994278315, "ce": 6.3641486167907715, "genuineness": 4.432034492492676, "identity": 0.545425295829773, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/15657882f58ea32dc4994f0ae14d6ea7bbc853e73cd64234e35258fad7c5a009.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "163e7292d7ce4bfdbff87f9d0ebe005c7b9bb480bad0b719859c9df11a405536", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "20b3113156dc3e73323e5dd377c47061e7a1401a6d03cad2e3d62d78c146aa03", "generation_seconds_batch": 17.400363913970068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21470078825950623, "target_z": -0.011718742847893999, "ce": 5.9431867599487305, "genuineness": 4.68307638168335, "identity": 0.4849385619163513, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/163e7292d7ce4bfdbff87f9d0ebe005c7b9bb480bad0b719859c9df11a405536.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "1685b25f34239e16e8ec915169f8a91d43f8effa9504be1c9721cfed3429b876", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a5ff5544542fabf2fb4ba25a5433fc5750b4af5bd79731846964c9ab3877c4c2", "generation_seconds_batch": 25.589102189056575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1542975902557373, "target_z": -0.1601562743171604, "ce": 4.981131076812744, "genuineness": 4.293961524963379, "identity": 0.3456633687019348, "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_Bitterness/1685b25f34239e16e8ec915169f8a91d43f8effa9504be1c9721cfed3429b876.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "16a77a9c9a89ba6af9b3912cffd1eaf14a41cec9049388506ac57faf7a6765fd", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0e3f5c5f3abe6951cfd347aec2910858e0d695e0d06b8ad1b33096f884f273b7", "generation_seconds_batch": 21.236929983948357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09151007235050201, "target_z": -0.3144531405915911, "ce": 6.078212261199951, "genuineness": 4.6203155517578125, "identity": 0.6368201971054077, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/16a77a9c9a89ba6af9b3912cffd1eaf14a41cec9049388506ac57faf7a6765fd.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "172654eca9d4e9570c79c472328f32bd0e1d7bbb6832d96f3c5ca6dab145552e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "7e25667332bd23d14081c4e214387527e6ef0039794904043c59bb2c5937e4b3", "generation_seconds_batch": 18.56904657499399, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14078636467456818, "target_z": -0.19335936684659916, "ce": 5.665193557739258, "genuineness": 4.319066047668457, "identity": 0.5810417532920837, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinspringen.", "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_Bitterness/172654eca9d4e9570c79c472328f32bd0e1d7bbb6832d96f3c5ca6dab145552e.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "179dac31cb8e2a912a016e114f4f910c29487d86f55b3800690e4a34d05ad8b0", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c6c7b80536aafa1f6177aaa2aa26fb06cd756f84818b592651702fb98af8ddd9", "generation_seconds_batch": 17.480037036933936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.060513705015182495, "target_z": -0.3906250057216848, "ce": 6.125868320465088, "genuineness": 4.595211505889893, "identity": 0.6515352129936218, "hypothesis": "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_Bitterness/179dac31cb8e2a912a016e114f4f910c29487d86f55b3800690e4a34d05ad8b0.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "17cc4bef3ca2e20914b1baed88467f93d158573dec3b0b822fbb284a24b4b005", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5a2b21fe7e622d4618ed62cad124fa7f635e79eb8fe7e772afe6162488ba1e36", "generation_seconds_batch": 23.35575611004606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03746512532234192, "target_z": -0.4472656205656943, "ce": 6.3641486167907715, "genuineness": 4.2249250411987305, "identity": 0.6060495376586914, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/17cc4bef3ca2e20914b1baed88467f93d158573dec3b0b822fbb284a24b4b005.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "17f64e94ec7659b7c8b57fda65cae8f201a53153a64dbc7077a218c3e402d648", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fb999e28ac6016beeeb8d493722704664ccb1c682647fdb9c4afb47fb3d83aaf", "generation_seconds_batch": 23.737628203001805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1423759162425995, "target_z": -0.1894531314368954, "ce": 6.1020402908325195, "genuineness": 4.7834930419921875, "identity": 0.7501490712165833, "hypothesis": "J'ai J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/17f64e94ec7659b7c8b57fda65cae8f201a53153a64dbc7077a218c3e402d648.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": "1802b7ff59580ae02d9c1e19a728ac36f91303ed9df527c29634c60e50678eee", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The keys are on the kitchen table.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3293e07e54181080a8f5e2fc3cca0b3514580e355a867e43e8abdf659fff1bfc", "generation_seconds_batch": 25.243173866998404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02077476680278778, "target_z": -0.488281257152106, "ce": 6.38003396987915, "genuineness": 4.570107460021973, "identity": 0.3766143321990967, "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_Bitterness/1802b7ff59580ae02d9c1e19a728ac36f91303ed9df527c29634c60e50678eee.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "183d2d767966654e00206086f78da71c5668c8368739d5f4834cccdfcb4390d5", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5f53f7b4a19ab842471c919a1522e5a4e3535eefa24b57b8a5dbf1615d8bd3e3", "generation_seconds_batch": 23.528279343037866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1264803409576416, "target_z": -0.22851563200906388, "ce": 6.133810997009277, "genuineness": 4.808597087860107, "identity": 0.6732456684112549, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/183d2d767966654e00206086f78da71c5668c8368739d5f4834cccdfcb4390d5.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "18b9b1fdf3abd84c386e1a84006c395e5cdbb0b55d6261ae6c6b6b9dacc11369", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "dcb24f7e6eec8f00d66613156195c0471b164d91f06db5e855efb83c048bec5e", "generation_seconds_batch": 23.032943513942882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035875558853149414, "target_z": -0.4511718925941808, "ce": 6.1894097328186035, "genuineness": 4.049196243286133, "identity": 0.7010896801948547, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/18b9b1fdf3abd84c386e1a84006c395e5cdbb0b55d6261ae6c6b6b9dacc11369.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "18e4d6866a28655f29df2493f41be887f0d9273e510956a416b2d3816b9cfd54", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5a1cd247f859e955ea2acc857ca1ba37eb9b6ed2853183cfad53f92aaee76f49", "generation_seconds_batch": 20.654469102970324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.117737777531147, "target_z": -0.25, "ce": 6.165581703186035, "genuineness": 4.519899368286133, "identity": 0.6327483654022217, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/18e4d6866a28655f29df2493f41be887f0d9273e510956a416b2d3816b9cfd54.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "19002a71c7715b392439aa546240dfa15c4877094ba9139c38fc7d68180d958a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e13cd1abab5acb9444f3e86e113e9e2be6e60804541b60e036ee716202421b1d", "generation_seconds_batch": 25.426297956029885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05393442511558533, "target_z": -0.6718749805462717, "ce": 6.284721851348877, "genuineness": 4.582659721374512, "identity": 0.44185471534729004, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/19002a71c7715b392439aa546240dfa15c4877094ba9139c38fc7d68180d958a.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "19219b0ebf32cd9e1c912e47f48659d42fc759cb9d2460421722d946955ee3a7", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "93d40c0109d1517613004e76f827591016ad1a234865c2f5d0e5ea74d9669edb", "generation_seconds_batch": 20.884542836924084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2480814903974533, "target_z": 0.07031249370614671, "ce": 5.80021858215332, "genuineness": 4.532451152801514, "identity": 0.18496040999889374, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/19219b0ebf32cd9e1c912e47f48659d42fc759cb9d2460421722d946955ee3a7.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": "19a9147ccc06e5779b28614d69bbb2f9fc6b3ffee433db36849b3e7a1fc9ad44", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Your message arrived after I had left.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f2b62de749e3ba219f994194f1f56afbcfb8f8a8b6314dd054ae5794991b9de7", "generation_seconds_batch": 18.293989134021103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3315332531929016, "target_z": 0.27539060340063987, "ce": 6.395919322967529, "genuineness": 4.582659721374512, "identity": 0.22075343132019043, "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_Bitterness/19a9147ccc06e5779b28614d69bbb2f9fc6b3ffee433db36849b3e7a1fc9ad44.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "19c73f1d127faca3d0202d58a0039456d20ce11fe68b706700613a0dae140657", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "309013db3a50279c57ee8a483d3179e4a32ab8034b470a6a1f1ff4cda379095a", "generation_seconds_batch": 17.035305746947415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11137954890727997, "target_z": -0.2656249965669891, "ce": 5.33954381942749, "genuineness": 4.344170093536377, "identity": 0.5103850364685059, "hypothesis": "La puerta hija abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.13333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/19c73f1d127faca3d0202d58a0039456d20ce11fe68b706700613a0dae140657.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "1a3101fb8b31526c1aa47250613f6a240d1ce325eea9fb57b42f0c135f76bbf1", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "11a8f79a5c5c7c3f9cefb42c1bbd1aeccd453f6dfad710b29ae21bde54fcfd73", "generation_seconds_batch": 17.860719718039036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40703725814819336, "target_z": 0.46093753604661425, "ce": 5.9431867599487305, "genuineness": 4.193545341491699, "identity": 0.3531981110572815, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/1a3101fb8b31526c1aa47250613f6a240d1ce325eea9fb57b42f0c135f76bbf1.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "1a3d09d9c74eeef26156a7656c499c2c1da2c4a4efd9f4d9ca5c3646d5004118", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f472a9fe5cce9c227f7a8d961765644f9714e9031271c7673092b18e6234e871", "generation_seconds_batch": 24.34188304201234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20595821738243103, "target_z": -0.03320312914822148, "ce": 6.300607204437256, "genuineness": 4.833701133728027, "identity": 0.8096860647201538, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/1a3d09d9c74eeef26156a7656c499c2c1da2c4a4efd9f4d9ca5c3646d5004118.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "1af98225fc4ca2f46371a992a1e503c4d1264aaf072c8bdaccb8e549a23efef2", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7591b50e8993c10fcc00ae1a8f03d1ac931e32eae6db85d62f6a8009b7328e73", "generation_seconds_batch": 23.000613381969742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09309963881969452, "target_z": -0.3105468685631046, "ce": 6.125868320465088, "genuineness": 3.998987913131714, "identity": 0.26598188281059265, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/1af98225fc4ca2f46371a992a1e503c4d1264aaf072c8bdaccb8e549a23efef2.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "1b72eb6469ced5a99206b454fb129cdb8ea82bb910d14b85e019c11d965ae3ec", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "178cd71429119d410ed5cbbceb2323e3bd381ae9cb8bf587543965faa986b732", "generation_seconds_batch": 22.705748685984872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006247714161872864, "target_z": -0.554687515448549, "ce": 5.919358730316162, "genuineness": 4.645420074462891, "identity": 0.278812050819397, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/1b72eb6469ced5a99206b454fb129cdb8ea82bb910d14b85e019c11d965ae3ec.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": "1c1548c4dddd72213272aa7f5e882e469263228b044b4ade7c32416c9ae45aa8", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b90d87719b812d3b90e6525569786f4a4bd212941961855cd6bf4fa1983e0515", "generation_seconds_batch": 16.256222896976396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21390600502490997, "target_z": -0.01367187886213724, "ce": 6.109982967376709, "genuineness": 4.331617832183838, "identity": 0.40213632583618164, "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_Bitterness/1c1548c4dddd72213272aa7f5e882e469263228b044b4ade7c32416c9ae45aa8.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "1c2d245868abf79b41087bab7fedd6a803afa234d5e76af9d3556cb0428ba66a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2f087ddf69c986fc2f102d55ad876fac5316c750c653092bbf9c45214931f7b3", "generation_seconds_batch": 22.52820741897449, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025543436408042908, "target_z": -0.476562514304212, "ce": 5.935244083404541, "genuineness": 4.7332844734191895, "identity": 0.5843852758407593, "hypothesis": "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_Bitterness/1c2d245868abf79b41087bab7fedd6a803afa234d5e76af9d3556cb0428ba66a.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "1cc796c7bd819db45064db2c5dd2c033f2e05bff855a6ebbc4d42afb79f967d3", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b7999975997cde4da9db80d72ea8c52becb4f9f8ecbed32043b474342b61f23f", "generation_seconds_batch": 22.600528057082556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12250644713640213, "target_z": -0.238281257152106, "ce": 6.1020402908325195, "genuineness": 4.293961524963379, "identity": 0.5342881679534912, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/1cc796c7bd819db45064db2c5dd2c033f2e05bff855a6ebbc4d42afb79f967d3.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "1d3cf79b5985375f94e92f704416e227f7a4130eaf68d39a56422cffd83c3510", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "656672caafa85665c815c35b6e642a1cf328d2f6532348605748f9de435e8ecc", "generation_seconds_batch": 23.430117720970884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26914313435554504, "target_z": 0.12207032344272219, "ce": 6.070269584655762, "genuineness": 4.770940780639648, "identity": 0.7776440978050232, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/1d3cf79b5985375f94e92f704416e227f7a4130eaf68d39a56422cffd83c3510.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "fe7c2c87bc0be00d499de7588f45023016e39f869be420964a3f75650360b397", "generation_seconds_batch": 17.27277183905244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.036670342087745667, "target_z": -0.44921875657993754, "ce": 6.221180438995361, "genuineness": 4.331617832183838, "identity": 0.613370418548584, "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_Bitterness/1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3.mp3" }, { "id": "heldout-de-1", "language": "de", "sentences": [ "Die Schlüssel liegen auf dem Küchentisch.", "Ich suchte in der Schublade... dann neben dem Fenster.", "Nimm sie mit, wenn du gehst." ], "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-1", "key": "1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "bd26c363286b50e98ae6c48bc04bf37543ea348fe6b473b8217551e921b62a4a", "generation_seconds_batch": 16.701746012899093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08038318157196045, "target_z": -0.34179686169708284, "ce": 6.3641486167907715, "genuineness": 4.369274139404297, "identity": 0.525143027305603, "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_Bitterness/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "1dd8f029efe5558c541dbb242d2e279e1ae2cdc7b148276541c971906508a0b9", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6ab56711a0569272f4915c6adb15cb892ba6f3ff93ff4212c04ea6ba097b96bf", "generation_seconds_batch": 21.355889252969064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08912573754787445, "target_z": -0.32031251201553806, "ce": 6.149696350097656, "genuineness": 4.557555198669434, "identity": 0.6816842555999756, "hypothesis": "La porte 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_Bitterness/1dd8f029efe5558c541dbb242d2e279e1ae2cdc7b148276541c971906508a0b9.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "1dec61919d33bdc810ca7de5656a7fbd6ea056619d8947299f6c564966cb3fa0", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2de8d85100bf4119d5d3dded51818d1de3bff9d3cc39c0a8d3db6f4501372300", "generation_seconds_batch": 23.22800625709351, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07879361510276794, "target_z": -0.3457031337255693, "ce": 6.109982967376709, "genuineness": 4.532451152801514, "identity": 0.5037424564361572, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/1dec61919d33bdc810ca7de5656a7fbd6ea056619d8947299f6c564966cb3fa0.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "1e03b5702030def7bad165c9adbaccfef5638b7ee0aa56585ab103e4aadbb00e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2b298390285c20767d7ed2c5707e4ae75431fb88b7f5efd62624cce1d71d752b", "generation_seconds_batch": 17.290502845076844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41736936569213867, "target_z": 0.4863281211378628, "ce": 6.141753673553467, "genuineness": 4.406930446624756, "identity": 0.41514474153518677, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/1e03b5702030def7bad165c9adbaccfef5638b7ee0aa56585ab103e4aadbb00e.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "b00ee00ac3e0fcc76439dea3de893bf2766df029781c75b2e2cad7e063142f30", "generation_seconds_batch": 17.27277183905244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003289639949798584, "target_z": -0.5312499931339782, "ce": 6.23706579208374, "genuineness": 4.381826400756836, "identity": 0.7535502910614014, "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_Bitterness/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "1f758c7a874766ebacc74297c0b1653da304c53f17e6829eea77caaa1ce06a3b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "de4abd29d004b1a29672d882593c8ebaddaf6d39e74997bfd134f8ee52143e90", "generation_seconds_batch": 17.400363913970068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16939839720726013, "target_z": -0.12304687314045244, "ce": 5.327630043029785, "genuineness": 4.6705241203308105, "identity": 0.011368708685040474, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/1f758c7a874766ebacc74297c0b1653da304c53f17e6829eea77caaa1ce06a3b.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "1f772c44091901de4a80f37b1aa3af53d84111a1d77a078560ec01606fddb7dd", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b70af2ac28127ab5f02e1c64d902c48fb7b37e492cf72daa50aa80dc532474a7", "generation_seconds_batch": 24.34188304201234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1614506095647812, "target_z": -0.14257812342653667, "ce": 6.141753673553467, "genuineness": 4.570107460021973, "identity": 0.6856978535652161, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/1f772c44091901de4a80f37b1aa3af53d84111a1d77a078560ec01606fddb7dd.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "1ff71ab40629c0070e794e897150f8254c75880b8f9e882de307baa81162eb67", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9f66e90278bcd7405452798f0866019a2d96fe1f92aaf4eb0239695329b05a69", "generation_seconds_batch": 27.44938614300918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1908574253320694, "target_z": -0.07031249370614671, "ce": 6.09409761428833, "genuineness": 4.231201171875, "identity": 0.6818252801895142, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/1ff71ab40629c0070e794e897150f8254c75880b8f9e882de307baa81162eb67.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "206d7e91155e3a4a303c2c6dc0eca37d18bff7befd55dc9fa89f028519a1bba3", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4ebcfdb1970d2c1d0e22594119774b31a2f8683143baf4e992bb150c1f81bd2f", "generation_seconds_batch": 18.166900111944415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13760724663734436, "target_z": -0.2011718742847894, "ce": 5.919358730316162, "genuineness": 4.331617832183838, "identity": 0.425141841173172, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/206d7e91155e3a4a303c2c6dc0eca37d18bff7befd55dc9fa89f028519a1bba3.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "20c3acfb71b88083bdf3e3bae2e6af4744c3101ed5bb9f4f48452dc0bf5132ca", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d3c2d10e6f8c4a694c2af6a03c6dd232df4c3fec3ee82e4aef415b3146e5f9cd", "generation_seconds_batch": 23.279515890055336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03349122405052185, "target_z": -0.45703126401812777, "ce": 6.395919322967529, "genuineness": 4.218649387359619, "identity": 0.6833781003952026, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/20c3acfb71b88083bdf3e3bae2e6af4744c3101ed5bb9f4f48452dc0bf5132ca.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "20dc8b1e9e915f780e61ab6848f9d57e31f8ad477f240522a70b4a82b3745821", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "04573c1c96c70a292b53de6fe548e1cb109ebd6122043bdaf1e5b1a0200a26b8", "generation_seconds_batch": 22.896398673998192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06289803981781006, "target_z": -0.3847656342977378, "ce": 5.831989288330078, "genuineness": 4.356721878051758, "identity": 0.3578203022480011, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/20dc8b1e9e915f780e61ab6848f9d57e31f8ad477f240522a70b4a82b3745821.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "2124b6db4827962c82716db48eb411fde44d732a8d94bee2f48a3869cc67bc22", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9169864e284cb9dbb4560f2c73e4a057aa90ba6f2c6db89a0a3c439f87da79f0", "generation_seconds_batch": 18.12146454595495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13442812860012054, "target_z": -0.20898438172297965, "ce": 6.356205940246582, "genuineness": 4.507347106933594, "identity": 0.15313781797885895, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2124b6db4827962c82716db48eb411fde44d732a8d94bee2f48a3869cc67bc22.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "21b13d778f3ef999434d5020aabc3436f1012f23380a1f73287a7d524e9ae9ea", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0d628fa1d01d78d3ede08deaaff408f8370a0e1d2298c98b26cad97021825d9d", "generation_seconds_batch": 23.220287385978736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19324176013469696, "target_z": -0.06445312228219972, "ce": 5.935244083404541, "genuineness": 4.7458367347717285, "identity": 0.723623514175415, "hypothesis": "La porte 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_Bitterness/21b13d778f3ef999434d5020aabc3436f1012f23380a1f73287a7d524e9ae9ea.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "21bb0b8f64f75509c0844a2ca079fa4ff68121c25adaebe9af69d48f127d0e59", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2fb9152b05c4dfdb1628cc82be38678d0f606a103461fd7630aa276e08340ee6", "generation_seconds_batch": 23.079717120039277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21072688698768616, "target_z": -0.021484386300327483, "ce": 5.279973983764648, "genuineness": 4.444586753845215, "identity": 0.7636173963546753, "hypothesis": "j'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/21bb0b8f64f75509c0844a2ca079fa4ff68121c25adaebe9af69d48f127d0e59.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "220b3978ab618aefdd316aebd8c7c7caa94979231ac8c2be520d80f2a526428a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "06ca91a012f1293a3e939db47d299b53939b6f500c1de04bbe21b93f1d53d100", "generation_seconds_batch": 22.03444226202555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0517711341381073, "target_z": -0.4121093920220123, "ce": 6.117925643920898, "genuineness": 4.080576419830322, "identity": 0.3932327330112457, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/220b3978ab618aefdd316aebd8c7c7caa94979231ac8c2be520d80f2a526428a.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "2222c555b003e869d63d8a9f175a7369e983bc0450e1b1632b05c0fa42cdb04b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "66d3c5c8ba8ae0763cb2a7d42bc06b13501db51135c619101adb45ad73cbf38c", "generation_seconds_batch": 22.484765358967707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08038318157196045, "target_z": -0.34179686169708284, "ce": 5.967014789581299, "genuineness": 4.532451152801514, "identity": 0.7358574867248535, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2222c555b003e869d63d8a9f175a7369e983bc0450e1b1632b05c0fa42cdb04b.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "22275df06e669ba6b5673c5bfc58a75ea5a477a8d4a50fd8c9fa2fa00d64e17e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0734abee1053f5f6ab15aa3c9022109bc86a764f627865f5ef9c3ecb5cf3d11b", "generation_seconds_batch": 23.7612807599362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11296910792589188, "target_z": -0.261718742847894, "ce": 5.871703147888184, "genuineness": 4.231201171875, "identity": 0.5664602518081665, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/22275df06e669ba6b5673c5bfc58a75ea5a477a8d4a50fd8c9fa2fa00d64e17e.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": "2239a4976ac43074668da3e5e71bf8bd6933cfd61ba124cc9c3d060aab7dfc31", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6fbaddc93d83a1b205ca617400c4ac842d20480c158d199efb35d048d399799c", "generation_seconds_batch": 23.34040217893198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2202642410993576, "target_z": 0.001953136014243242, "ce": 6.141753673553467, "genuineness": 4.532451152801514, "identity": 0.7252091765403748, "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_Bitterness/2239a4976ac43074668da3e5e71bf8bd6933cfd61ba124cc9c3d060aab7dfc31.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "229602bb2737fb84561f0a9ddd9617204f02593094de77a45bb903e6f4a896bb", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9596da2fd5601951723b9d7de2b34a7882be2017daed8ffafd025ee975ec6c28", "generation_seconds_batch": 22.33491800900083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12330123037099838, "target_z": -0.23632812113786275, "ce": 6.109982967376709, "genuineness": 4.281409740447998, "identity": 0.7959508895874023, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/229602bb2737fb84561f0a9ddd9617204f02593094de77a45bb903e6f4a896bb.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": "2303fcc1924457b62cdd75dff6e1a72a5b1960dd1c97152d9062471970afa8ea", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8b1360f191dad7170e5a1210a26becd5099a14e70f60a198d7af9c4d83213f0f", "generation_seconds_batch": 18.022021715994924, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16621927917003632, "target_z": -0.1308593805786427, "ce": 5.704906940460205, "genuineness": 4.381826400756836, "identity": 0.5633946657180786, "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_Bitterness/2303fcc1924457b62cdd75dff6e1a72a5b1960dd1c97152d9062471970afa8ea.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "23834abe47e0ee1d5edabba439492962f48c5a23de2914132e15a1c37dcd52fb", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d29f81b720231731776df90e4f100295da2e48ae4a21bae0a9de4273df7679bd", "generation_seconds_batch": 25.60686301300302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012826979160308838, "target_z": -0.5078125074381903, "ce": 5.990842819213867, "genuineness": 4.570107460021973, "identity": 0.30034005641937256, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/23834abe47e0ee1d5edabba439492962f48c5a23de2914132e15a1c37dcd52fb.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "23c9a23a9fbb99da765a1ec5045ff3b94da14249cb25ace0c6735c5610b75f84", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2653118c6e66907e8384340570f747ebc925e97bcc2a3b61f11253988a17e2f9", "generation_seconds_batch": 27.44938614300918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2981525659561157, "target_z": 0.19335940346538188, "ce": 6.062326908111572, "genuineness": 4.344170093536377, "identity": 0.4454041123390198, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/23c9a23a9fbb99da765a1ec5045ff3b94da14249cb25ace0c6735c5610b75f84.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "241f07e488d197502afcfe1384693cad3cacea299d97ae11182cf89d717f1895", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b0e73c9e8dd3fbef2f534a53716fbcca875ce94b23b349febf12306c232c4346", "generation_seconds_batch": 16.594955797074363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03803884983062744, "target_z": -0.6328124799741032, "ce": 6.308549880981445, "genuineness": 4.7081804275512695, "identity": 0.514115035533905, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/241f07e488d197502afcfe1384693cad3cacea299d97ae11182cf89d717f1895.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "248d86fedd8ae897f6fe028567d250f63c17aa657dab8102c9097827f1c549ac", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "14031b857c8c96f38baac77caa0b53064379f9213065838cb126f3afd5fea742", "generation_seconds_batch": 23.903164339018986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21549555659294128, "target_z": -0.009765643452433482, "ce": 5.728734970092773, "genuineness": 4.770940780639648, "identity": 0.5621887445449829, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/248d86fedd8ae897f6fe028567d250f63c17aa657dab8102c9097827f1c549ac.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "24c547726a9826988ba3d0c560e579a8ed47d42f81e111504c6e36ba72ed83a7", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b4c971ae80febc6c761395ff83373aa779a8acdbc68c900555c4c8e91f2168d9", "generation_seconds_batch": 22.87373704498168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13919681310653687, "target_z": -0.1972656022563029, "ce": 5.879645347595215, "genuineness": 4.821148872375488, "identity": 0.5428809523582458, "hypothesis": "La porte 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_Bitterness/24c547726a9826988ba3d0c560e579a8ed47d42f81e111504c6e36ba72ed83a7.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "258cb13687ee98f8e5a5ae7ce3ca51e17869c1f7535f6ec558d047e098942b7a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7392077b7e4f3b33b209ad6743bdd764cbf424bdc6ce8f1d80b14ac5afc1732e", "generation_seconds_batch": 20.919797790935263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.164629727602005, "target_z": -0.13476561598834644, "ce": 5.728734970092773, "genuineness": 4.632867813110352, "identity": 0.5245989561080933, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/258cb13687ee98f8e5a5ae7ce3ca51e17869c1f7535f6ec558d047e098942b7a.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": "267260ccd2e070bbb7e5fd4dcd3c037ded69e83039b930c83b5ecefc59c112a2", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f022e2b361977578a287b722893e2c9bfcc1274efc13ceabca9d1ca10595e038", "generation_seconds_batch": 16.332715074997395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07879361510276794, "target_z": -0.3457031337255693, "ce": 6.181467056274414, "genuineness": 4.557555198669434, "identity": 0.6011968851089478, "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_Bitterness/267260ccd2e070bbb7e5fd4dcd3c037ded69e83039b930c83b5ecefc59c112a2.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "1a1f7b0ef416e7712f37b330918226c5601e442360783a4ae992a89434282367", "generation_seconds_batch": 19.66906708793249, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0064687579870224, "target_z": -0.523437485695788, "ce": 6.38797664642334, "genuineness": 4.432034492492676, "identity": 0.24381817877292633, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "26d3097cc9e06b58dca9f6e30ccb0d883dc88a17d6eeb4d934ec025bd62b8ad5", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "677344475deabe23e167bfc760ef90f9a75ba8d246beb79797b63c122aafde25", "generation_seconds_batch": 23.842542489990592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13601768016815186, "target_z": -0.2050781463132759, "ce": 6.09409761428833, "genuineness": 4.808597087860107, "identity": 0.6304784417152405, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/26d3097cc9e06b58dca9f6e30ccb0d883dc88a17d6eeb4d934ec025bd62b8ad5.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "2706d1d6f90b07706c19a1468233b34304b0b5eaf1b7c456279369c9cf65580c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d856ad1fa118daa3e4540c7f6e84eeb7d8f5bc5686aee725e0262f0e05366616", "generation_seconds_batch": 16.024652096093632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.164629727602005, "target_z": -0.13476561598834644, "ce": 6.24500846862793, "genuineness": 4.331617832183838, "identity": 0.5245944261550903, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2706d1d6f90b07706c19a1468233b34304b0b5eaf1b7c456279369c9cf65580c.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": "2718d386292c130a60ad92bd34d65831a57dad28086b303371307252ba7ce9dd", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e0955cfe1fa0b375e1efb3183960e1b051d34c006662aadc921ae9e76f44b067", "generation_seconds_batch": 18.585794584010728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2290067970752716, "target_z": 0.023437485695787998, "ce": 6.165581703186035, "genuineness": 4.20609712600708, "identity": 0.18802766501903534, "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_Bitterness/2718d386292c130a60ad92bd34d65831a57dad28086b303371307252ba7ce9dd.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "2763f4ab417324bc8f55f2a6bbdfb77696ed1c76c1638541e0717273c1b593f4", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c2186eba8b9f1b7b6f7bcdc193c1e7a9ebe81cb7f82ecdadb8734bbd59695adb", "generation_seconds_batch": 23.032943513942882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003068596124649048, "target_z": -0.5468750080103587, "ce": 6.260893821716309, "genuineness": 4.2249250411987305, "identity": 0.4892866909503937, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2763f4ab417324bc8f55f2a6bbdfb77696ed1c76c1638541e0717273c1b593f4.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "28d0b98a48517d8bcf17421004c8aa1bf9eb8a0a2c765ffadec6010bc50d2229", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "216f0b56ddce52c3353f55322694ad2fa4e2fdb82bf42098b7708b7647ca0cb6", "generation_seconds_batch": 22.811391772003844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.143965482711792, "target_z": -0.18554685940840893, "ce": 6.117925643920898, "genuineness": 4.432034492492676, "identity": 0.5904359817504883, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/28d0b98a48517d8bcf17421004c8aa1bf9eb8a0a2c765ffadec6010bc50d2229.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "28e217eb8ce222e346f79699bc80e167d5656ccfcfbc8c0993ff377eff3da038", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "503e5ad3c4c8986bebd8b7c1bc85792186a559ee32aecff5138a9219ba1c00ef", "generation_seconds_batch": 16.798076200997457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10502132028341293, "target_z": -0.28124999313397825, "ce": 6.181467056274414, "genuineness": 4.6203155517578125, "identity": 0.38568568229675293, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/28e217eb8ce222e346f79699bc80e167d5656ccfcfbc8c0993ff377eff3da038.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "2aa1aa5b4daecca1249a3726d85aece9858f8ba94b534a0f53878aeca8b64b7b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "403574486238a7a7e62e1c598ee4eed58cfd03ccc6f09d91730a0429ac889bcb", "generation_seconds_batch": 23.533210065914318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21946945786476135, "target_z": 0.0, "ce": 6.062326908111572, "genuineness": 4.419482707977295, "identity": 0.21346428990364075, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2aa1aa5b4daecca1249a3726d85aece9858f8ba94b534a0f53878aeca8b64b7b.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "2ade4d85c85fa1a8aefa8c6ac0a00b4bd4ca467df163de4c8a711eb652977707", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "92725050942fcdfcb6dd900cd8286330f1007f650890869aa9be5627882e0fa1", "generation_seconds_batch": 16.28955731203314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05256591737270355, "target_z": -0.41015625600776906, "ce": 5.903473377227783, "genuineness": 4.7458367347717285, "identity": 0.5841745138168335, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2ade4d85c85fa1a8aefa8c6ac0a00b4bd4ca467df163de4c8a711eb652977707.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "2aecfa6f94032fbeefc8648cc0c1e6bd7d1d8367671f65cc21fd7ced74ccb1c9", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "781b15a5e313204cf955f1dc3426a88a4c6006c707711ff2c24b14a6caca856f", "generation_seconds_batch": 23.512912012985907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08038318157196045, "target_z": -0.34179686169708284, "ce": 5.530168056488037, "genuineness": 4.281409740447998, "identity": 0.6070422530174255, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2aecfa6f94032fbeefc8648cc0c1e6bd7d1d8367671f65cc21fd7ced74ccb1c9.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "2b15bedec76104249c6ba12dd380a2bc0e02dc0fd65fe5bfc8949c568dd60569", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f0678658b5d6a6b4e81fce82fb4af0cff18a1829215a4d4da809c060af319cb3", "generation_seconds_batch": 21.086783951963298, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16860361397266388, "target_z": -0.12500000915469567, "ce": 5.903473377227783, "genuineness": 4.796044826507568, "identity": 0.6089596152305603, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2b15bedec76104249c6ba12dd380a2bc0e02dc0fd65fe5bfc8949c568dd60569.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": "2b6a08e66f0a2a9be3496e32eb36e10bed2d234725bb6ab6da3c9851a2e2c27d", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7f2aa367d4c46a312922ac74e408ab1e654a65399066dd92fe135aef25357b3b", "generation_seconds_batch": 17.059975925949402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23854415118694305, "target_z": 0.046875008010358724, "ce": 6.0305562019348145, "genuineness": 4.419482707977295, "identity": 0.5249082446098328, "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_Bitterness/2b6a08e66f0a2a9be3496e32eb36e10bed2d234725bb6ab6da3c9851a2e2c27d.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "2bb09d7141896284bd0f049158f618d9c21393f09ea8afd8e54b184e4f1ad751", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8f5121b3017695289f8c945f021b1dca0dac8a44c46b69770ad2c8e0972e83ec", "generation_seconds_batch": 22.645195971941575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5787094831466675, "target_z": 0.88281257152106, "ce": 5.816103935241699, "genuineness": 4.262581825256348, "identity": 0.33471304178237915, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2bb09d7141896284bd0f049158f618d9c21393f09ea8afd8e54b184e4f1ad751.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "2bfa1a3cdafc9f049a919e573e1d025772d60d932a9f445ca632a748d386866e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "31809460dac35df6b29f650d272dd17f6781f80aa4901a47f64260a8399500ac", "generation_seconds_batch": 23.34191469999496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.020553722977638245, "target_z": -0.5898437439922309, "ce": 6.24500846862793, "genuineness": 4.017816066741943, "identity": 0.2629585862159729, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2bfa1a3cdafc9f049a919e573e1d025772d60d932a9f445ca632a748d386866e.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "2c341245ada45d812bbb3fe7183edbfd19a29395b3daf13bb7d69284635fb18b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "924800620efaebce039999f6734a721fae8bbf11d3a2c17c43971a30057ac24b", "generation_seconds_batch": 24.235803941031918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12886467576026917, "target_z": -0.2226562605851169, "ce": 6.117925643920898, "genuineness": 4.519899368286133, "identity": 0.3848731219768524, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2c341245ada45d812bbb3fe7183edbfd19a29395b3daf13bb7d69284635fb18b.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "2cc90aa88cd489eca51f26d48adcef9924c29ae042d8093de9238176ae8ef6ce", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "36dbd745853c8091a78e4fec96cb2f1589cb34c1fc20ef470688eb5ac0b0ce6b", "generation_seconds_batch": 17.45161718199961, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17416706681251526, "target_z": -0.11132813029255845, "ce": 5.95112943649292, "genuineness": 4.331617832183838, "identity": 0.5458464622497559, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2cc90aa88cd489eca51f26d48adcef9924c29ae042d8093de9238176ae8ef6ce.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "2d3a5c68f4d0300aa6cc42b5fdd4b18d2795240032b8b55e59bcd424535a1953", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "61b46765c82ad986cb718c63879aa4bc24a0bfddf2ff3119838b04bd896252db", "generation_seconds_batch": 18.31573661090806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03349122405052185, "target_z": -0.45703126401812777, "ce": 6.141753673553467, "genuineness": 4.871357440948486, "identity": 0.6323346495628357, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2d3a5c68f4d0300aa6cc42b5fdd4b18d2795240032b8b55e59bcd424535a1953.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "2d7500f9c283d2907fdbe204b4b46e6753117f9c8a53d017b91f108fadcdbfdb", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "699a710e2ed09b1c6e32aa464e8846cd72ede58baf8bbd15ce319791b1a8138c", "generation_seconds_batch": 22.826042141998187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20277909934520721, "target_z": -0.04101563658641172, "ce": 6.1894097328186035, "genuineness": 4.632867813110352, "identity": 0.564211905002594, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2d7500f9c283d2907fdbe204b4b46e6753117f9c8a53d017b91f108fadcdbfdb.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "2e051db4f55b1dfc97288fce3ec431d6274e7999f46c58ee8932eb6d9a5bfde1", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e8856cacb1793dea0d8293179b61b6fb8592e7b7cf7f71a4d2711298fbb817a8", "generation_seconds_batch": 24.806034008972347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.430880606174469, "target_z": 0.5195312502860843, "ce": 5.418970584869385, "genuineness": 4.1998209953308105, "identity": 0.1896498203277588, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás libre.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2e051db4f55b1dfc97288fce3ec431d6274e7999f46c58ee8932eb6d9a5bfde1.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "2e0ed0105f1cf735d35a4f708744c37de4d4000ba639a1e6a81e51b63e539310", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ed302990855706750d98414568fb997d8bbed4f5ebb11d61db43f9f008fb0b0c", "generation_seconds_batch": 23.349480285076424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2305963635444641, "target_z": 0.02734375772427448, "ce": 5.895530700683594, "genuineness": 4.507347106933594, "identity": 0.43700554966926575, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2e0ed0105f1cf735d35a4f708744c37de4d4000ba639a1e6a81e51b63e539310.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": "2e2a15d8f33f4e9ed8a1822390a472cfec59349f5d95329c7a7e9f93ffe5d5aa", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2ba9e42f33a589b249b6ebdbfe142f1203bc4114f66ac5af7b3b82f44018f9cf", "generation_seconds_batch": 17.524931850959547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17814096808433533, "target_z": -0.10156248684012496, "ce": 6.109982967376709, "genuineness": 4.808597087860107, "identity": 0.7857652902603149, "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_Bitterness/2e2a15d8f33f4e9ed8a1822390a472cfec59349f5d95329c7a7e9f93ffe5d5aa.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "2e5c4614947e4bca75b2d96fdef9aeecfbf590869d79c7838ec07f68d9470b6c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fcd881a19ede14bac06bc94c1260559031f070f63ad559e3110ab0d4eeec5ad3", "generation_seconds_batch": 25.190924953087233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08594663441181183, "target_z": -0.3281249828349456, "ce": 6.316492557525635, "genuineness": 4.557555198669434, "identity": 0.5954412221908569, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2e5c4614947e4bca75b2d96fdef9aeecfbf590869d79c7838ec07f68d9470b6c.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "2e917d946f3da3059e6527a47efcee70298b5da8d6a4171ac534d62ebfb2af4c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e425da2aa84b4f5744b0df68f94e17196a1c5df023439b1dd58b344c876cd6b6", "generation_seconds_batch": 21.655805955058895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2667587995529175, "target_z": 0.11621095201877518, "ce": 5.704906940460205, "genuineness": 4.193545341491699, "identity": 0.35914546251296997, "hypothesis": "Ik heb het een klein doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2e917d946f3da3059e6527a47efcee70298b5da8d6a4171ac534d62ebfb2af4c.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": "2f0c6dcfd1ba5d7450cb53c4f385b2d70f9c6e0d96ca0b68031a1e1af4c79086", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Escribí el número en el sobre.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1c2c1673db39751657d5a7d0c25974babf3de27523712de58f4ef5a6d74b481c", "generation_seconds_batch": 15.850789993070066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1980104297399521, "target_z": -0.05273437943430572, "ce": 6.062326908111572, "genuineness": 4.6705241203308105, "identity": 0.7392885684967041, "hypothesis": "Escribí el número en el sobre, léelo bien, y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2f0c6dcfd1ba5d7450cb53c4f385b2d70f9c6e0d96ca0b68031a1e1af4c79086.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "2f62963311437be105a57113955114f1ee096900ff82c4f7ce0663eca5efc5ac", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "239aff0b2279343eb753c133e73231e16f8aa3797ed7fd33d7631adbfd76b479", "generation_seconds_batch": 23.171261124080047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9506659507751465, "target_z": 1.7968750995573155, "ce": 4.811356067657471, "genuineness": 4.030367851257324, "identity": 0.41787856817245483, "hypothesis": "La puerta sigue abierta y he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/2f62963311437be105a57113955114f1ee096900ff82c4f7ce0663eca5efc5ac.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "2fa7dc254d1cb6dccff3fc87194839d5f1f8ee266a14a21c85c80122724f644a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4994497b08146f9ad627e32fb7c92f9ada260c87858c2bc23277d14a9218ab17", "generation_seconds_batch": 24.806414193008095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09786830842494965, "target_z": -0.2988281257152106, "ce": 5.331601142883301, "genuineness": 4.6203155517578125, "identity": 0.6801542639732361, "hypothesis": "La porte 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_Bitterness/2fa7dc254d1cb6dccff3fc87194839d5f1f8ee266a14a21c85c80122724f644a.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": "2fd52e3e1154cd79b576dfa3d2ca75eec40cfec3a5a9757a3885e803eae82d94", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c71dd68c7beaf8454bbc6cfd37bd84bc6e9d7f5b1d174edf7438962915e68d8", "generation_seconds_batch": 20.259648323990405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09945786744356155, "target_z": -0.29492187199611547, "ce": 5.95112943649292, "genuineness": 4.7458367347717285, "identity": 0.7018152475357056, "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_Bitterness/2fd52e3e1154cd79b576dfa3d2ca75eec40cfec3a5a9757a3885e803eae82d94.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "301dbeb7ffa0c513f0bcddd294c64c2ce3ddd67d3d844cd86b37f515fef37b2e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "af7031d59880f6f0f851ec3c1d6123fe557e7cac88e3e07afe811fdfe49b360d", "generation_seconds_batch": 23.09461022692267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014416545629501343, "target_z": -0.5039062354097038, "ce": 6.403861999511719, "genuineness": 4.519899368286133, "identity": 0.4456399083137512, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/301dbeb7ffa0c513f0bcddd294c64c2ce3ddd67d3d844cd86b37f515fef37b2e.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "303fbdeb395074333bae15987eaa89cb56235185f03940582f5a7456be7d57ba", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e669029f63d2285bdf5f211139bd100b66ddf5dd12d2c26bdd68ef6b768dec0e", "generation_seconds_batch": 23.33658838190604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2011895477771759, "target_z": -0.04492187199611548, "ce": 6.09409761428833, "genuineness": 4.356721878051758, "identity": 0.49300622940063477, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/303fbdeb395074333bae15987eaa89cb56235185f03940582f5a7456be7d57ba.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "306ee62c5bbe617cd61376d12c545badfd1425a527b4ae12d497b2758ffbe221", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e2a740490d72c8e16a41e047cc9e19819cbb0df02f4f656cc7eafbd176a72cc2", "generation_seconds_batch": 23.582927935989574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0724353939294815, "target_z": -0.36132811198316706, "ce": 6.125868320465088, "genuineness": 4.457139015197754, "identity": 0.7293708324432373, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/306ee62c5bbe617cd61376d12c545badfd1425a527b4ae12d497b2758ffbe221.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "308c95f5b377190ff6470876ee232ad2de3983031ff5b71c1516c2c200a0a7f3", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3ef32975fdae571e3425f8afce304539cb8a81ea320ea55da32a8ce5e264e7de", "generation_seconds_batch": 23.60560069407802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1614506095647812, "target_z": -0.14257812342653667, "ce": 5.903473377227783, "genuineness": 4.306513786315918, "identity": 0.2726351320743561, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/308c95f5b377190ff6470876ee232ad2de3983031ff5b71c1516c2c200a0a7f3.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "30cb06e05ca7b60d2812780474828dd13c820472446cf4d849e6d51f4bc1fe29", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "41629ce053c756ff621b7334f1bc6b96c0d72b9865e35f0b4ab3c1f6ff3976ca", "generation_seconds_batch": 21.357082108035684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12250644713640213, "target_z": -0.238281257152106, "ce": 5.478540420532227, "genuineness": 4.519899368286133, "identity": 0.7419899702072144, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/30cb06e05ca7b60d2812780474828dd13c820472446cf4d849e6d51f4bc1fe29.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "30f60bd00d3d2369284e5381d1306a5563a2111bb1357e100719ac8dd6db484d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "07ece8934f51183a6bd43641e3c8558fb983c506fbd07b24c35720f61d5bfd98", "generation_seconds_batch": 22.484765358967707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08356228470802307, "target_z": -0.33398439087767534, "ce": 5.911416053771973, "genuineness": 4.808597087860107, "identity": 0.7178447246551514, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/30f60bd00d3d2369284e5381d1306a5563a2111bb1357e100719ac8dd6db484d.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "312e696834d0d93daf5f3ad7e163fb844be208132433dafc000e4d6150cf5598", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "805fd04b361dab00df177b8558eca7a067623cba8d7212dcd9da5609067d9ce4", "generation_seconds_batch": 22.966008196002804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16621927917003632, "target_z": -0.1308593805786427, "ce": 5.911416053771973, "genuineness": 4.356721878051758, "identity": 0.3062184453010559, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/312e696834d0d93daf5f3ad7e163fb844be208132433dafc000e4d6150cf5598.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "33e08b797df81982922eec2516f0b73848a5547810359ff9fa6370627f16b0db", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3c7f07b14dd46cc27815f5a3bf90954398c6af7b8743611babffceb41a7a162d", "generation_seconds_batch": 17.27816205995623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.015785053372383118, "target_z": -0.578125001144337, "ce": 6.038498878479004, "genuineness": 4.494794845581055, "identity": 0.6586179733276367, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/33e08b797df81982922eec2516f0b73848a5547810359ff9fa6370627f16b0db.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "bab15dafbcd34d9a8f0ee3af65924348d5d0f3b0906f42b7faff1aca11104cfe", "generation_seconds_batch": 16.67309578100685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11853255331516266, "target_z": -0.24804688229514812, "ce": 6.1020402908325195, "genuineness": 4.300237655639648, "identity": 0.5811840295791626, "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_Bitterness/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.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": "34420599d4b569e0a2cf37220257a5aa74052f64d7d70435ea467bf7ae6c713f", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6f9082ee645c63f02ffec960771f4c5911dd52b78a74038aefcef9f389fd4310", "generation_seconds_batch": 21.96685098297894, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15032370388507843, "target_z": -0.16992188115081117, "ce": 6.141753673553467, "genuineness": 4.8588056564331055, "identity": 0.690414309501648, "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_Bitterness/34420599d4b569e0a2cf37220257a5aa74052f64d7d70435ea467bf7ae6c713f.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": "3448ff17cf85a5e7ef2b25a022e4b41ed55feefcd7fe600d699c2011b24b6903", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "596f4fb66374cb9b3c737623eb2583b3ec45eb6cbac7987be78f5f7862f39eeb", "generation_seconds_batch": 23.552643514005467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12091689556837082, "target_z": -0.24218749256180977, "ce": 5.546053409576416, "genuineness": 4.482243061065674, "identity": 0.5427966117858887, "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_Bitterness/3448ff17cf85a5e7ef2b25a022e4b41ed55feefcd7fe600d699c2011b24b6903.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b1987b0c1d93a81dd9f8d69ee4b4579d1c09dee020115a7020738531b782874e", "generation_seconds_batch": 17.60378365998622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09071530401706696, "target_z": -0.3164062399870516, "ce": 6.435632705688477, "genuineness": 4.105680465698242, "identity": 0.34468740224838257, "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_Bitterness/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "348235be015ebe075fa38af3cca15d0c4e44c6cbbf48b60e66afbabdfcd088d3", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7b1b842250149f5aaf8106d1a68cf284065796cc995120ac2cdb8c11b8a618e4", "generation_seconds_batch": 21.294508069986477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02077476680278778, "target_z": -0.488281257152106, "ce": 6.117925643920898, "genuineness": 4.8588056564331055, "identity": 0.6894553899765015, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/348235be015ebe075fa38af3cca15d0c4e44c6cbbf48b60e66afbabdfcd088d3.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "34e2b681d267de70fcbab8237c4c0a2c754bb99ee726d5e415e61024f435a6b2", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8dc199ea8e0d9ac0056327d34a857138d4249e83b4f0153fd00df4c66b390713", "generation_seconds_batch": 15.419242302072234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11296910792589188, "target_z": -0.261718742847894, "ce": 6.197352409362793, "genuineness": 4.482243061065674, "identity": 0.25588229298591614, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/34e2b681d267de70fcbab8237c4c0a2c754bb99ee726d5e415e61024f435a6b2.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": "352992ce12b87a08823116766096a92e915899c1fcd43dab8f6530fc4012ce4f", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Someone moved the little blue chair.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bce743c490b1d84ddf8700f9bf46b10c161c42d9c9b28e1f3466692f1ba1b2e0", "generation_seconds_batch": 25.658768982975744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13124901056289673, "target_z": -0.21679688916116988, "ce": 6.356205940246582, "genuineness": 4.494794845581055, "identity": 0.13552787899971008, "hypothesis": "Someone moved the little blue chair. I used to stand here beside the tall bookshelf. We can put it back after lunch.", "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_Bitterness/352992ce12b87a08823116766096a92e915899c1fcd43dab8f6530fc4012ce4f.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "36aec57808e228598801c064fca516b8bcf909c57e614422930116fa5ed473cd", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "290aa7dc40c73bcaa81f211de9874c23c73098a2881efc368bd5a4301b847b2a", "generation_seconds_batch": 16.90050096390769, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23218591511249542, "target_z": 0.03124999313397824, "ce": 5.95112943649292, "genuineness": 4.6705241203308105, "identity": 0.48008590936660767, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/36aec57808e228598801c064fca516b8bcf909c57e614422930116fa5ed473cd.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "36b3a3405b76ed7c42c2284d1e976aae211bbc0db62edeea4841b55f0eb05355", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d2787c282f80c9f1a9f0024a15a02654d7078b3f1dc6825bd5b6aa5e4c5176c0", "generation_seconds_batch": 21.420424425043166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1264803409576416, "target_z": -0.22851563200906388, "ce": 6.125868320465088, "genuineness": 4.394378662109375, "identity": 0.5773431658744812, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/36b3a3405b76ed7c42c2284d1e976aae211bbc0db62edeea4841b55f0eb05355.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "36d119379a166924a079ae2b666a990f00bf27fe1dba7ca0df837f139a104118", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "bca5b46d15617b7f448f36795ffbf541e645fd456cb1ec15e47a7774050a9779", "generation_seconds_batch": 22.050783179933205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16939839720726013, "target_z": -0.12304687314045244, "ce": 5.546053409576416, "genuineness": 4.406930446624756, "identity": 0.3580980598926544, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/36d119379a166924a079ae2b666a990f00bf27fe1dba7ca0df837f139a104118.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "37afa1ad2574a96160199540c14fa01c2399cafac204b341cdaf8aa4edfcfd02", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2165514688861da5adf11db8f442b0866c5536f2cefad5bb0e8d703ab2faeb8f", "generation_seconds_batch": 14.849936492042616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12489078938961029, "target_z": -0.23242186741876764, "ce": 6.356205940246582, "genuineness": 4.545003414154053, "identity": 0.3690376877784729, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/37afa1ad2574a96160199540c14fa01c2399cafac204b341cdaf8aa4edfcfd02.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "3872a3179a96934afb95da57267ea6e668f26cc475212e8812677acf434b99c6", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fe8cd7cf772090bae79184d23d0798c3645ad30a6b32ff81d5d87ee1f04acf68", "generation_seconds_batch": 21.41195596207399, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00011052191257476807, "target_z": -0.5390625005721685, "ce": 6.38003396987915, "genuineness": 4.507347106933594, "identity": 0.46426814794540405, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3872a3179a96934afb95da57267ea6e668f26cc475212e8812677acf434b99c6.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "38ddc1fc5b95d227e4278f35207e3da32ab5d1294ca8cf967eedfb8a2b87fbe0", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b64fa179b7e695c6aa88267be093defb7e706281248e72f2eabdf3a181b0fc60", "generation_seconds_batch": 16.620169023051858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1749618500471115, "target_z": -0.1093749942783152, "ce": 6.062326908111572, "genuineness": 4.65797233581543, "identity": 0.8399683833122253, "hypothesis": "La porte 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_Bitterness/38ddc1fc5b95d227e4278f35207e3da32ab5d1294ca8cf967eedfb8a2b87fbe0.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "38f83537c08ce42b1a78cac36e27a168a6821b887c1c2fca7a5c3c11f2b584f9", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8d28da1627fc0203b974dd0e36f4f8e0b8a17d06cd957cd2ded5ac2e563d1d46", "generation_seconds_batch": 22.21567549498286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.018964171409606934, "target_z": -0.5859375085825272, "ce": 6.292664527893066, "genuineness": 4.557555198669434, "identity": 0.39681124687194824, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/38f83537c08ce42b1a78cac36e27a168a6821b887c1c2fca7a5c3c11f2b584f9.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": "38fd3c4d113d5bb0021a23e1b39b66c803fd79f6f1ce60e1998b095e034e3a48", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "222b985fbac9d4fae903d8e523430fba0f2df8b612571269cf74969f0c1afa8d", "generation_seconds_batch": 17.555713724112138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09151007235050201, "target_z": -0.3144531405915911, "ce": 5.80021858215332, "genuineness": 4.946669578552246, "identity": 0.7624237537384033, "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_Bitterness/38fd3c4d113d5bb0021a23e1b39b66c803fd79f6f1ce60e1998b095e034e3a48.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "3902437ae80c8fcf4d4e3f61fa77f54f396ec7cd1c504b3798e7388ca0474384", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "66ed9a519f7bccce8361b827000713cb6cc581c9b63a0d4a7eabf033eea4985d", "generation_seconds_batch": 23.340684319031425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08912573754787445, "target_z": -0.32031251201553806, "ce": 5.617537498474121, "genuineness": 4.268857479095459, "identity": 0.6494981050491333, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3902437ae80c8fcf4d4e3f61fa77f54f396ec7cd1c504b3798e7388ca0474384.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "397392d7b22f5ca41cdd021a410e444d7ddb1426943f58e25a70f55caaaeab68", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4e9a4b6a51bb5d34ab3ac1bd44e571dfee1f75a4a1519bbe5f50e9fb15aa6af1", "generation_seconds_batch": 21.998680577031337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2083425521850586, "target_z": -0.02734375772427448, "ce": 5.959072113037109, "genuineness": 4.356721878051758, "identity": 0.4070213735103607, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/397392d7b22f5ca41cdd021a410e444d7ddb1426943f58e25a70f55caaaeab68.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "399ef3b9b16e00a23c4186142676713127eaf86618393dd2c19089aafaf5a93b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4a69bacafaa51c707d1bd17fe35e4e60963b1741b6377ddcac304a27d79f1334", "generation_seconds_batch": 17.47609936702065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09230485558509827, "target_z": -0.31250000457734783, "ce": 6.086154937744141, "genuineness": 4.482243061065674, "identity": 0.8241745233535767, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/399ef3b9b16e00a23c4186142676713127eaf86618393dd2c19089aafaf5a93b.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "3ae920d611781d1c52af62f5ba9cefe01292f0b7d8a8aabb8018f6f1e834560a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "659c4c07020d3f0ef210937f4a0adcd67998c5271153fbf0117aa3ffa4c13dcb", "generation_seconds_batch": 24.728989872033708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11217432469129562, "target_z": -0.2636718788621372, "ce": 6.284721851348877, "genuineness": 4.6705241203308105, "identity": 0.7651721239089966, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3ae920d611781d1c52af62f5ba9cefe01292f0b7d8a8aabb8018f6f1e834560a.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": "3aee9f100b56aacd19e18d0c62d4c712e55362af4d9fb174fa1bc6f7a3b3d7cd", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "75c65245d88029e1be24ccef9cbe39417aeaf25a4c516cf41c35677dfcb74ef3", "generation_seconds_batch": 18.022021715994924, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24172326922416687, "target_z": 0.05468751544854896, "ce": 5.998785495758057, "genuineness": 4.532451152801514, "identity": 0.8199297189712524, "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_Bitterness/3aee9f100b56aacd19e18d0c62d4c712e55362af4d9fb174fa1bc6f7a3b3d7cd.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "3b60b27802aa42d8c8660f6d1b4b769c18c24033182a03b5a5488c3c31f6f6b9", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "33b48bbdc17582b58371d71c9072abe239f055142e28bbf9a444961b94423c4a", "generation_seconds_batch": 22.704433702048846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3442497253417969, "target_z": 0.30664063315340084, "ce": 5.144948482513428, "genuineness": 3.9927117824554443, "identity": 0.35024595260620117, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3b60b27802aa42d8c8660f6d1b4b769c18c24033182a03b5a5488c3c31f6f6b9.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "3b6a82fbf78e8ea480211d4a0cd059de1ff0e26376fc0eafd4aceb3b88ee897f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fee8566543ea3deada551a1c93468ddd37743e99de7853d2fadcd1c93c855fa4", "generation_seconds_batch": 22.901264299987815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05415548384189606, "target_z": -0.4062499839792826, "ce": 6.046441555023193, "genuineness": 4.607763767242432, "identity": 0.7395417094230652, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3b6a82fbf78e8ea480211d4a0cd059de1ff0e26376fc0eafd4aceb3b88ee897f.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "3b7da8c5bfa0d3635225ac47768ab45f9780d050cfdf94736dfb15a18fd3d120", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "867e952a9b11f2b1d1fd7704c14c23a9b1ab51fa72fe097f7f500a6191a3adb5", "generation_seconds_batch": 23.383268150035292, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09071530401706696, "target_z": -0.3164062399870516, "ce": 6.109982967376709, "genuineness": 4.607763767242432, "identity": 0.5331120491027832, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3b7da8c5bfa0d3635225ac47768ab45f9780d050cfdf94736dfb15a18fd3d120.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "3b802355ecb3eff4d0d69d4d2785c4eb0ae9264ebfe7f5bfb4cd7b6c41584ae7", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f68dd7e0ec40849505861900230965e73fd7778aad8074a6325bf9488308e351", "generation_seconds_batch": 20.210499681998044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08435706794261932, "target_z": -0.3320312548634321, "ce": 6.205295085906982, "genuineness": 4.6956281661987305, "identity": 0.6918182373046875, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3b802355ecb3eff4d0d69d4d2785c4eb0ae9264ebfe7f5bfb4cd7b6c41584ae7.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "3b8611dd385fdc1cbbd19039a9d348569dfe763ae5e0cff9d448dd7251ba91ac", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e31f4ccaa5b144fd16a76acb3b9aac503ba0309429e6990121be93fa65ebfd85", "generation_seconds_batch": 18.470095761003904, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05971892178058624, "target_z": -0.39257814173592803, "ce": 5.95112943649292, "genuineness": 4.193545341491699, "identity": 0.42175981402397156, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3b8611dd385fdc1cbbd19039a9d348569dfe763ae5e0cff9d448dd7251ba91ac.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "3b89769de04cd675efd03fa61663f37571dbbaabeb934baf3a26b682a3280b42", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "381c04d6ed03d3ee4bfd84d067351868443b8d97728f47617f3a17b0bfa38eef", "generation_seconds_batch": 18.56904657499399, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10502132028341293, "target_z": -0.28124999313397825, "ce": 5.824047088623047, "genuineness": 4.419482707977295, "identity": 0.5230517387390137, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3b89769de04cd675efd03fa61663f37571dbbaabeb934baf3a26b682a3280b42.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "3bed19ae54cc24b2e1e0a429f1025d8b3ec1f46ba0efdc98b87878442a5b4b95", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c11d4de687b9c739369ddc12aa15ac7d0d199b67fe1f8634b65bd27173d62b77", "generation_seconds_batch": 23.849276897963136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20754778385162354, "target_z": -0.029296857119735, "ce": 6.181467056274414, "genuineness": 4.65797233581543, "identity": 0.592239499092102, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3bed19ae54cc24b2e1e0a429f1025d8b3ec1f46ba0efdc98b87878442a5b4b95.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "3bf4d9301591c5c9e872fd788f306779aa0f34da03fdee2d497ef3073cacb271", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e2887360a6d51307afd144dca7c7f7252f476c834311a9fb5357f08e9e72711c", "generation_seconds_batch": 26.31037823902443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16939839720726013, "target_z": -0.12304687314045244, "ce": 6.054384231567383, "genuineness": 4.6203155517578125, "identity": 0.760709285736084, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3bf4d9301591c5c9e872fd788f306779aa0f34da03fdee2d497ef3073cacb271.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "3bf9a8cbc8ad4b8f6b843c10f1cc25fa910a814ff594df9c3437feefca27ede6", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "055179f8c1d8b98faedac85a44713f49a5961963e00238053d0fe51adad1431a", "generation_seconds_batch": 15.949503679992631, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2564266622066498, "target_z": 0.09082029368996122, "ce": 5.6413655281066895, "genuineness": 4.325342178344727, "identity": 0.5490196943283081, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschopfen.", "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_Bitterness/3bf9a8cbc8ad4b8f6b843c10f1cc25fa910a814ff594df9c3437feefca27ede6.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": "3c328b3f299d145f386066aa3124c383258202c5d3cead9dd67f251aa1670ed6", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "903041d3b5d968169f417e04d90b91f48b644eae4b44ef8b981cdd166ac508e6", "generation_seconds_batch": 18.686993557028472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11853255331516266, "target_z": -0.24804688229514812, "ce": 6.125868320465088, "genuineness": 4.557555198669434, "identity": 0.48110100626945496, "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_Bitterness/3c328b3f299d145f386066aa3124c383258202c5d3cead9dd67f251aa1670ed6.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "3c3ad28c44f1f9bf3070d7630dcff76b2109a9bd3c71744bad26d816383c6d78", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9c71ec5d1b5c7c253ffcdf59b370fbeba537741dfec7bdcfd9fe39753a5e3f4c", "generation_seconds_batch": 23.47615922393743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10104742646217346, "target_z": -0.2910156182770204, "ce": 5.847874641418457, "genuineness": 4.65797233581543, "identity": 0.7238436341285706, "hypothesis": "La porte 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_Bitterness/3c3ad28c44f1f9bf3070d7630dcff76b2109a9bd3c71744bad26d816383c6d78.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "187e01a67405e2722315c15f1904a3b80e97e2a751b90edf5143fc8d70cef71c", "generation_seconds_batch": 16.189613151014782, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06289803981781006, "target_z": -0.3847656342977378, "ce": 6.252951145172119, "genuineness": 4.319066047668457, "identity": 0.47448277473449707, "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_Bitterness/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "3c5f706ec36b7e0a088315895e39986886d8bc972cf411079c30e27f375f5bfe", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "afe4d69638a19307430d1466f85c2312c1c58cfad984cf0a8eef7ccbe815b8f7", "generation_seconds_batch": 22.79008430801332, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.047797247767448425, "target_z": -0.42187499885566304, "ce": 6.197352409362793, "genuineness": 4.758388519287109, "identity": 0.6688574552536011, "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_Bitterness/3c5f706ec36b7e0a088315895e39986886d8bc972cf411079c30e27f375f5bfe.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "3d05f7dcf34bb596bef96a5df72476e2d5e23df94ba0230b56538510aa186725", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "60905d754f51a4babdc3872341b56e031f1a6bf148667b6d521cac0cac6a7f53", "generation_seconds_batch": 21.85766258800868, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1280699074268341, "target_z": -0.2246093599805774, "ce": 6.0146708488464355, "genuineness": 4.268857479095459, "identity": 0.427467942237854, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3d05f7dcf34bb596bef96a5df72476e2d5e23df94ba0230b56538510aa186725.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": "3d37244f3d3355613096ede1c5666ff1f9d2bdc67ac633d67a098031e58d92bc", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e0e38aad9ec29800a267fc4af0f1d3e07b5c3d38884b0d85175e5d7028f85259", "generation_seconds_batch": 22.675173102063127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11137954890727997, "target_z": -0.2656249965669891, "ce": 6.1020402908325195, "genuineness": 4.532451152801514, "identity": 0.3997458815574646, "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_Bitterness/3d37244f3d3355613096ede1c5666ff1f9d2bdc67ac633d67a098031e58d92bc.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "3d813bdbeb2e9a10efb07a63d728e86797641020103d2c447a25094ec9d209c2", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "60645e1f7d4d76116c3f8eb2de6744072c33d2c865dcd5a6e3a4be5c548d72da", "generation_seconds_batch": 23.920489523909055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16065582633018494, "target_z": -0.1445312594407799, "ce": 5.6334228515625, "genuineness": 4.507347106933594, "identity": 0.3534061312675476, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3d813bdbeb2e9a10efb07a63d728e86797641020103d2c447a25094ec9d209c2.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "3d8c5a08f8cc5ea48c27efbdc8b4bfe8f71d705334d73c4d9821870db87dd3d8", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "77f4d713a10c91a1963aac24113d23afff9b764cd8831717947b5646f13ee04e", "generation_seconds_batch": 21.655805955058895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3299437165260315, "target_z": 0.27148440460971884, "ce": 5.752562999725342, "genuineness": 4.293961524963379, "identity": 0.18367619812488556, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3d8c5a08f8cc5ea48c27efbdc8b4bfe8f71d705334d73c4d9821870db87dd3d8.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "3dcf09b990412a4d82a22e7bfd2ef97c1b05e978957e942c1fe6c4e68c8bcb13", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8372a4a3ad95b33b28c9e8357ea01f6cb7d8cfa3bfdde5808845006ad8d0a180", "generation_seconds_batch": 23.34191469999496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07323016226291656, "target_z": -0.35937501258770654, "ce": 6.125868320465088, "genuineness": 4.168440818786621, "identity": 0.21528702974319458, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3dcf09b990412a4d82a22e7bfd2ef97c1b05e978957e942c1fe6c4e68c8bcb13.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": "3df324f074d07636558738fdc5d0bfd962766484a170ea69c83acfd8f31d572d", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1dd3f7831a26ff903a5145f63feab6f11b3bee4f44bdb7ae692dd79696529be3", "generation_seconds_batch": 17.886618123971857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20754778385162354, "target_z": -0.029296857119735, "ce": 5.959072113037109, "genuineness": 4.607763767242432, "identity": 0.5713775157928467, "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_Bitterness/3df324f074d07636558738fdc5d0bfd962766484a170ea69c83acfd8f31d572d.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "3e02e2a264e29ced1952ddd145d42c162d9c8a57df372943ebc15d4cdf1f4850", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9207585e14d5ad75810f51081768e8d8005e39ac38d99b2e85b5c416205e9a80", "generation_seconds_batch": 23.553593727992848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08117794990539551, "target_z": -0.33984376230162233, "ce": 5.998785495758057, "genuineness": 4.419482707977295, "identity": 0.7407896518707275, "hypothesis": "J'ai trouvé la petite boîte. Elle était prête de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3e02e2a264e29ced1952ddd145d42c162d9c8a57df372943ebc15d4cdf1f4850.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "3ea7b105d6ba6b6105e9a04f4f5476e26bb10b5380de9ef27a7c7ccd07b53a61", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b6329e36e9b65156139ba978193ed7d8e27b2f90a446db25e6177fda6bd1cbf7", "generation_seconds_batch": 18.98135552299209, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3943207859992981, "target_z": 0.42968750629385327, "ce": 5.784333229064941, "genuineness": 4.1998209953308105, "identity": 0.2206411063671112, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3ea7b105d6ba6b6105e9a04f4f5476e26bb10b5380de9ef27a7c7ccd07b53a61.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "3ed7b7563d34750804e2dad2ab2388b4024ab1ff259f0bb8faba4b99385312d6", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1abe43e695c8ee0c63f7c5476bdd7f9e4fd8d1fdfa3de011e4abfd4f5c1814b8", "generation_seconds_batch": 24.292780222021975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022364333271980286, "target_z": -0.48437498512361954, "ce": 6.125868320465088, "genuineness": 4.645420074462891, "identity": 0.6355687975883484, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3ed7b7563d34750804e2dad2ab2388b4024ab1ff259f0bb8faba4b99385312d6.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "3ee0cc517c10a2b6155cb7ee0a5666eba2c112948a42c171cebab21454699f76", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "218c00debc04469ba8770d3b8f25992928403de7a6bf53164c1411a36ba0d0bc", "generation_seconds_batch": 23.340684319031425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10502132028341293, "target_z": -0.28124999313397825, "ce": 5.9431867599487305, "genuineness": 4.394378662109375, "identity": 0.4710981845855713, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3ee0cc517c10a2b6155cb7ee0a5666eba2c112948a42c171cebab21454699f76.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "3ee68c6f62d6d6890d7a9f0e46d0deb25f99018f058916fb9bfd5c20e529f39d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5dd50d0d8ba26809d479d1da55d72bfc0ae708f39051911488244ddb54ca36d6", "generation_seconds_batch": 23.350299171055667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1423759162425995, "target_z": -0.1894531314368954, "ce": 6.125868320465088, "genuineness": 4.337893962860107, "identity": 0.49688753485679626, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3ee68c6f62d6d6890d7a9f0e46d0deb25f99018f058916fb9bfd5c20e529f39d.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "3ef642d17436bca35ad1f1b7706dc19a771b70485370eeae7f00233f3a2b63cd", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7eb2b0476205a7f2b8fb3ae1738fca77fc49a0425d04be64434b64084c0078ca", "generation_seconds_batch": 24.41931577399373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09468919038772583, "target_z": -0.30664063315340084, "ce": 5.919358730316162, "genuineness": 4.306513786315918, "identity": 0.4198993444442749, "hypothesis": "La porte 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_Bitterness/3ef642d17436bca35ad1f1b7706dc19a771b70485370eeae7f00233f3a2b63cd.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "3f8b6df94ae66b5dea3cb47f1092fa7ce24b0fee07395d720847410115740afa", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "54d430befa9dddb41760c4d432f9633265e989c4efed6b0d2322f26c27979b5c", "generation_seconds_batch": 24.032985058031045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10025264322757721, "target_z": -0.2929687542912636, "ce": 6.109982967376709, "genuineness": 4.262581825256348, "identity": 0.16490748524665833, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3f8b6df94ae66b5dea3cb47f1092fa7ce24b0fee07395d720847410115740afa.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "3ffeab4f530cf6f7393d47e2b3f3b94d4822599d14fd13a22c013d8453d43f58", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ea4002bb4ac9653af4423922dd95dac0262b22d17ebe4366d34f32e114216c6e", "generation_seconds_batch": 24.198599909897894, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0986630842089653, "target_z": -0.2968750080103587, "ce": 6.022613525390625, "genuineness": 4.821148872375488, "identity": 0.7631741762161255, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/3ffeab4f530cf6f7393d47e2b3f3b94d4822599d14fd13a22c013d8453d43f58.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "40265583c0f50f044c3067876f0304344031f67dde465d78a69d4b46cbc09be0", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ee64ebc10e393b286a63f4720133daa0f5d15c59affe4e4b26c00ea7a52c91ac", "generation_seconds_batch": 23.833496738923714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22264857590198517, "target_z": 0.00781250743819024, "ce": 6.157639026641846, "genuineness": 4.381826400756836, "identity": 0.40472084283828735, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/40265583c0f50f044c3067876f0304344031f67dde465d78a69d4b46cbc09be0.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "404a419d0a978e987641317b1dd6fc8c7a3d789a59c84686b2ccdbe92c70aca8", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "65adb7b0ca1041c0236562cb70042d88b0791bda14c7cee639d8cc8240a818b1", "generation_seconds_batch": 25.09198809391819, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23854415118694305, "target_z": 0.046875008010358724, "ce": 6.213237762451172, "genuineness": 4.6705241203308105, "identity": 0.6377160549163818, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/404a419d0a978e987641317b1dd6fc8c7a3d789a59c84686b2ccdbe92c70aca8.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": "407290a3ce89d2af6d83ceb9bfa6bda70dbc1891611213105763a7b270b0bcc7", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ba1701b6150ecfbf0625eff74e5ae6259c7e2394ae5fe2a9977259875e6d8ee1", "generation_seconds_batch": 23.374517517047934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13204379379749298, "target_z": -0.21484375314692664, "ce": 6.284721851348877, "genuineness": 4.457139015197754, "identity": 0.3997470736503601, "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_Bitterness/407290a3ce89d2af6d83ceb9bfa6bda70dbc1891611213105763a7b270b0bcc7.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "40a78d26b98ca9c434fee44a0e0fc28ff853efd093c842d1420096a1d43cc93f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8d6ab35992f7cf820142af7dcad52f58eddbdea187c38c0428f341298c6eb788", "generation_seconds_batch": 16.7087722819997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011237427592277527, "target_z": -0.511718742847894, "ce": 6.300607204437256, "genuineness": 4.6203155517578125, "identity": 0.45530715584754944, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/40a78d26b98ca9c434fee44a0e0fc28ff853efd093c842d1420096a1d43cc93f.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "40bcde887d24991d14278b83df82508c6db298c9e933af11d80efdf087ce8cd3", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "cab39f30a0971df1af09602fb6e7cc98f93d81af8638fef517ac3f13eba010cd", "generation_seconds_batch": 22.33491800900083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08833096921443939, "target_z": -0.3222656114109986, "ce": 6.006728172302246, "genuineness": 4.250029563903809, "identity": 0.3008370101451874, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/40bcde887d24991d14278b83df82508c6db298c9e933af11d80efdf087ce8cd3.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "40d02fdeb6fa8d709aa1957bb36d6624e8e5f4322d052e26cb3ee501c5104c21", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8c1e76098da61b1d7e1396afdeec095c5e4d6ea922db1c53ad92dd611c895c59", "generation_seconds_batch": 22.007780354004353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20595821738243103, "target_z": -0.03320312914822148, "ce": 5.855817794799805, "genuineness": 4.18726921081543, "identity": 0.5886632204055786, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/40d02fdeb6fa8d709aa1957bb36d6624e8e5f4322d052e26cb3ee501c5104c21.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "419cb4cd577db50761832e76dc803eb084137b2cc67e2cb127eec212d20c4415", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "955b5a54c72fa2564e7bd97eb70389268ecc8219f09bc6649b7b38e6327fa2a4", "generation_seconds_batch": 24.363633590051904, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1161482185125351, "target_z": -0.25390625371909514, "ce": 5.657250881195068, "genuineness": 4.557555198669434, "identity": 0.7625805139541626, "hypothesis": "La porte est encore ouverte. J'ai poussé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/419cb4cd577db50761832e76dc803eb084137b2cc67e2cb127eec212d20c4415.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "41ab777a2b8e5bbfce3798a6a1f186d7548bc6bdb0ade950730f6b3ab10a4a7d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "09f8302c600cd9e63eb1a6a2d3e26625a7f5d9816d79a66e2b825dee0760b5ca", "generation_seconds_batch": 24.407182850060053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16224539279937744, "target_z": -0.14062498741229343, "ce": 5.919358730316162, "genuineness": 4.68307638168335, "identity": 0.7003390192985535, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/41ab777a2b8e5bbfce3798a6a1f186d7548bc6bdb0ade950730f6b3ab10a4a7d.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "41b8b041cdd5028d5cc7b6363b14ec1b442f5e5c6377d10b4ea8347eaf5d5ecd", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "de37494c78e489083f4e90dc638bdc533d45401f66cc8eb32e20fe3893126750", "generation_seconds_batch": 23.83910462493077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023953884840011597, "target_z": -0.48046874971391573, "ce": 6.133810997009277, "genuineness": 4.2751336097717285, "identity": 0.2574191391468048, "hypothesis": "The door is still open. I'd put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/41b8b041cdd5028d5cc7b6363b14ec1b442f5e5c6377d10b4ea8347eaf5d5ecd.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "41f5105f52b203267ab0aa2ce1f091803b14f6644a00fbe9673385b664889b3e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "50e91980f5a06783fd06dd88f45220d68b82d24354b6ae543cf4a06b4c972bbd", "generation_seconds_batch": 25.34052395890467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10422653704881668, "target_z": -0.2832031291482215, "ce": 5.6532793045043945, "genuineness": 4.381826400756836, "identity": 0.18751707673072815, "hypothesis": "They found the little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/41f5105f52b203267ab0aa2ce1f091803b14f6644a00fbe9673385b664889b3e.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "424afe28e4301ebd19b2ef0cab11f5563ea22ce11316602f491d82265a6faa1d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f845d3b80391e7af3852552378c8e5e4fa94ff679410f760a537c89979fcce0c", "generation_seconds_batch": 24.593255235929973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11455865949392319, "target_z": -0.25781250743819023, "ce": 5.395142555236816, "genuineness": 4.381826400756836, "identity": 0.5533894300460815, "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_Bitterness/424afe28e4301ebd19b2ef0cab11f5563ea22ce11316602f491d82265a6faa1d.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "42e399448e1ece9d280e759d2e6106bd7c15c3e6f55a9e22c1a8b276442abfe1", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "cc395720eee80bc3b4b6d7a89dd19201b821755f64628e93b2a0818b45a255af", "generation_seconds_batch": 17.907444561016746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1614506095647812, "target_z": -0.14257812342653667, "ce": 5.748591423034668, "genuineness": 4.632867813110352, "identity": 0.5347409248352051, "hypothesis": "La porte 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_Bitterness/42e399448e1ece9d280e759d2e6106bd7c15c3e6f55a9e22c1a8b276442abfe1.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": "42e4a59ade8dc9ba9d4885f62bc2a25dca8dc79970a810fadb7617a98a0c702f", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The road turns left behind the bridge.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "be8ccbe579adabeb4cbba4bbb7a0d1ab8777c567b03f8194a26fb8d25f85d3f5", "generation_seconds_batch": 20.513461622060277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09707353264093399, "target_z": -0.30078124342006246, "ce": 6.332377910614014, "genuineness": 4.319066047668457, "identity": 0.28726905584335327, "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_Bitterness/42e4a59ade8dc9ba9d4885f62bc2a25dca8dc79970a810fadb7617a98a0c702f.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "432abe6b49e8d1d9c7aad726f89c56ae6d65b57292be9ce02171537227f7276d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "cb094fd72f68c6435f5869f6c0fc2465f124656c1951c5e10d2979c8aa9566f7", "generation_seconds_batch": 24.416166351991706, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09071530401706696, "target_z": -0.3164062399870516, "ce": 6.133810997009277, "genuineness": 4.394378662109375, "identity": 0.6243855357170105, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/432abe6b49e8d1d9c7aad726f89c56ae6d65b57292be9ce02171537227f7276d.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "43301317f224be17ba12cdb6add77c51702d49e055458fdcf8f44a9b00699f01", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "71ba88d08e4fbbdc8871a410c5db83eedaaaba172cf81f6d1dcf298adef7c52a", "generation_seconds_batch": 21.57100839400664, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17416706681251526, "target_z": -0.11132813029255845, "ce": 5.665193557739258, "genuineness": 4.532451152801514, "identity": 0.6832667589187622, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/43301317f224be17ba12cdb6add77c51702d49e055458fdcf8f44a9b00699f01.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "d0851a682cae5eb88c58eab264bb52d878cc1fc3a6b9ce381bce0a0a9200b719", "generation_seconds_batch": 16.67309578100685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13204379379749298, "target_z": -0.21484375314692664, "ce": 6.1894097328186035, "genuineness": 3.998987913131714, "identity": 0.6792938709259033, "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_Bitterness/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "43c53ad4cf19e74baf89d1e23dbefe32a5309667768c3ec846b7ff5cdf92d465", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "22975021816953e24683579638c965b7a988943135e8e645de804009c13701f1", "generation_seconds_batch": 23.099110975977965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029517337679862976, "target_z": -0.4667968708517785, "ce": 6.117925643920898, "genuineness": 4.432034492492676, "identity": 0.8309199810028076, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/43c53ad4cf19e74baf89d1e23dbefe32a5309667768c3ec846b7ff5cdf92d465.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "3a5183c5ac548355b23c611cd80242737204e9d7d369491c3d0a43ed45739e3d", "generation_seconds_batch": 17.561696356046014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06607715785503387, "target_z": -0.37695312685954757, "ce": 6.229123115539551, "genuineness": 4.595211505889893, "identity": 0.5029157996177673, "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_Bitterness/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "442c76a63c72a444639c513f25ba3039c17736737e0522a5c20f83e8ee93802c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "649346f15d9c184ad888a0a3a412a10c9b8fe2bc589611412a879e13d35a76bc", "generation_seconds_batch": 16.64944285596721, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0724353939294815, "target_z": -0.36132811198316706, "ce": 5.784333229064941, "genuineness": 4.7834930419921875, "identity": 0.5477262139320374, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/442c76a63c72a444639c513f25ba3039c17736737e0522a5c20f83e8ee93802c.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "44663f5aba8ce6fcdb468561d1039b1a8013f3488ef6fc8451a69b08ca79f00d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "83c9377de28f49a5ceafbd9068ac8ba31c6cbd69a9353078101d2f46f2b7363c", "generation_seconds_batch": 23.684670781018212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13760724663734436, "target_z": -0.2011718742847894, "ce": 5.7406487464904785, "genuineness": 4.7332844734191895, "identity": 0.7249115705490112, "hypothesis": "La porte 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_Bitterness/44663f5aba8ce6fcdb468561d1039b1a8013f3488ef6fc8451a69b08ca79f00d.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "45144d8d208efc732be49c7e92b5356d3a8476637f9d33aa4d815ff52f44a627", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2fb101414f0703624e8488b8052a3085f5a2db98d158fc8776efdd63d137d5d0", "generation_seconds_batch": 22.704433702048846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2202642410993576, "target_z": 0.001953136014243242, "ce": 5.4944257736206055, "genuineness": 4.300237655639648, "identity": 0.2273598611354828, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/45144d8d208efc732be49c7e92b5356d3a8476637f9d33aa4d815ff52f44a627.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": "45bcf6ba1f0a506a7defef73650729e792a3587479927c7f11c40e56276a974d", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "144475f30c7052f153abda06af8f345404692c824818b5ee40a17459f968eb54", "generation_seconds_batch": 17.059975925949402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1161482185125351, "target_z": -0.25390625371909514, "ce": 6.070269584655762, "genuineness": 4.570107460021973, "identity": 0.5516215562820435, "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_Bitterness/45bcf6ba1f0a506a7defef73650729e792a3587479927c7f11c40e56276a974d.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "45e34d34aa8a763b8fc2a2fa223455d5dbb91d494d3f9edbfa8f2c655a1d36b1", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ccc1d770d355fd7424ae95189820dbe73cd91cb755806f1d4429fabecc3176e8", "generation_seconds_batch": 24.205567545024678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24013370275497437, "target_z": 0.05078124342006248, "ce": 5.804190158843994, "genuineness": 4.419482707977295, "identity": 0.6107279062271118, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/45e34d34aa8a763b8fc2a2fa223455d5dbb91d494d3f9edbfa8f2c655a1d36b1.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "f15c0379788710b88277d6aab6025084ac86debd590420eb4867decc6298956f", "generation_seconds_batch": 20.428783176932484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031106889247894287, "target_z": -0.46289063544207476, "ce": 6.268836498260498, "genuineness": 4.18099308013916, "identity": 0.395742267370224, "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_Bitterness/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "46e2b7d600611c60cef775c79e5af57238f24397904dcd138ed7b82fa7a06013", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "763b26baf8eb7a7efb0ea39d63fc2948326fd25174fdc3344c48583d1085de1e", "generation_seconds_batch": 18.98135552299209, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3665035367012024, "target_z": 0.3613281486019498, "ce": 5.297844886779785, "genuineness": 4.344170093536377, "identity": 0.41638296842575073, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/46e2b7d600611c60cef775c79e5af57238f24397904dcd138ed7b82fa7a06013.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": "47158da462b4c3678dacbf1df939914dd29c6d5fbb31933e237080360fdd56d0", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Escribí el número en el sobre.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8e1629d0a6406f9e2f80a3330e5faded30fa0d75c653cdaf212668915ae9f8b6", "generation_seconds_batch": 24.154926970019005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10820043087005615, "target_z": -0.27343750400517935, "ce": 6.054384231567383, "genuineness": 4.494794845581055, "identity": 0.5363873839378357, "hypothesis": "Escribí el número en el sobre, léelelo bien, y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "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_Bitterness/47158da462b4c3678dacbf1df939914dd29c6d5fbb31933e237080360fdd56d0.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "4760130cc1f018a82c0e8ae4be9e4aab59c740de96ad97c19b119a7396e1ef5f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "067ce71989b3ef98d71df96a072cec088c76773c16389b4b295eebd7d24e0b12", "generation_seconds_batch": 21.46593455807306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04143901169300079, "target_z": -0.4375000137320435, "ce": 6.427689552307129, "genuineness": 4.632867813110352, "identity": 0.6405423879623413, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4760130cc1f018a82c0e8ae4be9e4aab59c740de96ad97c19b119a7396e1ef5f.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "4798c41e9d78272142760982657976ccaa27a2ede3f7eca7a46f35525a93d99d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2af136e1a02db97d74b160c5fc58cc8ce5bf4362a541b486886a4ffd918811bd", "generation_seconds_batch": 18.343920178012922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13045424222946167, "target_z": -0.2187499885566304, "ce": 5.411027908325195, "genuineness": 4.281409740447998, "identity": 0.023573201149702072, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuando estás lista.", "wer": 0.13333333333333333, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4798c41e9d78272142760982657976ccaa27a2ede3f7eca7a46f35525a93d99d.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "47b6306c40c36a2443315e3da322177aa37cba64e8a9560494d15ee9d895b8c4", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ea1ea150b0ee89ddf09041724ab6da3003c74c921cb005c916c2688484f620ed", "generation_seconds_batch": 23.15789654001128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05574503540992737, "target_z": -0.4023437485695788, "ce": 6.260893821716309, "genuineness": 4.319066047668457, "identity": 0.5073666572570801, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/47b6306c40c36a2443315e3da322177aa37cba64e8a9560494d15ee9d895b8c4.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "3b69efdb5bd153ea15ba4ef968da3434808e8cdca9202e5b7a203c96ebc3015d", "generation_seconds_batch": 17.915722636971623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05097636580467224, "target_z": -0.4140624914174728, "ce": 6.133810997009277, "genuineness": 4.457139015197754, "identity": 0.7131319046020508, "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_Bitterness/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.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": "47fc696af2fd2b31a1abe2932b7c91327bc955ffeff798a9d839ceef72b1f31b", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "12d10810915bfb91a48c07d475c1965ad3fa0a79cb79286236713791e4235772", "generation_seconds_batch": 17.937284872983582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11376388370990753, "target_z": -0.25976562514304213, "ce": 6.1020402908325195, "genuineness": 4.7332844734191895, "identity": 0.6888117790222168, "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_Bitterness/47fc696af2fd2b31a1abe2932b7c91327bc955ffeff798a9d839ceef72b1f31b.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "488c9168fc22ba9a85750cf9a27bd35370dfc4a28b149562b9176edc31c21d0b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c2d96cc723a6aaa7e65b3f403e4e1edb725bd81b1343dd94d472a4bde38b0e7d", "generation_seconds_batch": 24.591268897987902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09786830842494965, "target_z": -0.2988281257152106, "ce": 5.9431867599487305, "genuineness": 4.243753433227539, "identity": 0.5657353401184082, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/488c9168fc22ba9a85750cf9a27bd35370dfc4a28b149562b9176edc31c21d0b.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "48ff71d9b337b03617267c96cbdcff55243cc116ec9eeccc61a217b229f2f0f8", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7631260d2823b00774fc80e1badf9fe863c47a0757bb5538c7dca3183d5db949", "generation_seconds_batch": 22.53937918401789, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13204379379749298, "target_z": -0.21484375314692664, "ce": 6.054384231567383, "genuineness": 4.457139015197754, "identity": 0.3964511752128601, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het auke 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_Bitterness/48ff71d9b337b03617267c96cbdcff55243cc116ec9eeccc61a217b229f2f0f8.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "49160387e5d43f5a63802eee9c27e0c7ee79cf5209ffbb5a2ffbc108c054d129", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b6d3ef8f9dd5703083bb4305eb3ad1501eef3798b31c343e19700f62eefcf6fd", "generation_seconds_batch": 16.071710949065164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003289639949798584, "target_z": -0.5312499931339782, "ce": 6.205295085906982, "genuineness": 4.632867813110352, "identity": 0.7353190183639526, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/49160387e5d43f5a63802eee9c27e0c7ee79cf5209ffbb5a2ffbc108c054d129.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "494921397c47ee9210572ea2f4d44568e9a0538293719f1fbe073064138e964b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "dda4a5ed0ecba4e8144108889b87cbd833495b10ac9aa8599932a1aad32ca488", "generation_seconds_batch": 21.420424425043166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14714458584785461, "target_z": -0.1777343885890014, "ce": 6.09409761428833, "genuineness": 4.557555198669434, "identity": 0.35262781381607056, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg, maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/494921397c47ee9210572ea2f4d44568e9a0538293719f1fbe073064138e964b.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "49a5958d4233a17a7602678a1615a506feae4350a1654644caed4365cbbbf96a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "43cfffaee7139bfad62cce6b437489276b77d43498b2d9e83e78d4821fcee80c", "generation_seconds_batch": 28.749804561957717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09151007235050201, "target_z": -0.3144531405915911, "ce": 6.149696350097656, "genuineness": 4.770940780639648, "identity": 0.6420163512229919, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/49a5958d4233a17a7602678a1615a506feae4350a1654644caed4365cbbbf96a.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "49bc5882c93b6f14d6e814378a6fee6e6019f0c50205e917b385d44fd1d26d97", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e0516dfbe64085517c2ab5ec081d48bfea0632b4b7d7e2ea8b0181d74d3b9dfb", "generation_seconds_batch": 15.09683582407888, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03746512532234192, "target_z": -0.4472656205656943, "ce": 6.197352409362793, "genuineness": 4.268857479095459, "identity": 0.6699795722961426, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/49bc5882c93b6f14d6e814378a6fee6e6019f0c50205e917b385d44fd1d26d97.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "211d1e278272f9cbcb02c02fe157b108311f59ddf0bf63c57339060e9e727ad2", "generation_seconds_batch": 18.97841065202374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054950252175331116, "target_z": -0.404296884583822, "ce": 6.316492557525635, "genuineness": 4.300237655639648, "identity": 0.5990232229232788, "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_Bitterness/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "4ad7085db101927ccf29b5047c4854e7a15ea2beb12869546261f1b8f64a57ba", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0b24947d0c0d2218613118da77a44515569e6b338631d85a2d7965bf4e0d1cba", "generation_seconds_batch": 23.079100886010565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.07618823647499084, "target_z": -0.7265624959948206, "ce": 6.372091293334961, "genuineness": 4.413206577301025, "identity": 0.3003350496292114, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4ad7085db101927ccf29b5047c4854e7a15ea2beb12869546261f1b8f64a57ba.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "4ad70fd1ec08925e8b4d0660b164b9d14aa09bec92e6c7d3a12f3fdcd83f3dcf", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "82769ed77b6b9753e716e6aae7b6125da3948beae7729f2adfd42e0b9c0ee0f9", "generation_seconds_batch": 24.499026159988716, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02214328944683075, "target_z": -0.5937500160207174, "ce": 6.213237762451172, "genuineness": 4.482243061065674, "identity": 0.5061212182044983, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4ad70fd1ec08925e8b4d0660b164b9d14aa09bec92e6c7d3a12f3fdcd83f3dcf.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": "4b707f08fb3d0b0468893c0059ed79f72a3aebc18383ab16c1e01b6823a87be3", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "52f90d1c817640b3dd8887a640654b458d44c7d561dac83ca522f98d0cbc8c1e", "generation_seconds_batch": 23.105930309044197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1089952141046524, "target_z": -0.2714843679909361, "ce": 5.546053409576416, "genuineness": 4.532451152801514, "identity": 0.48716020584106445, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, le bien, et vérifié les deux derniers chiffres. Appelle moi quand tu auras un maman.", "wer": 0.13636363636363635, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4b707f08fb3d0b0468893c0059ed79f72a3aebc18383ab16c1e01b6823a87be3.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "4c4f00e733789fffd27002ee7e1a5acd4210dd82a8eda473177d21af48f21d0a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "be30e1ad81b807229b1a98201da042ff3c3fb14558622b4b1c11abd9441ba5a5", "generation_seconds_batch": 15.14416466106195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10581609606742859, "target_z": -0.27929687542912635, "ce": 6.1894097328186035, "genuineness": 4.287685871124268, "identity": 0.24742022156715393, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4c4f00e733789fffd27002ee7e1a5acd4210dd82a8eda473177d21af48f21d0a.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "4c7e46af47ec68e973acebbf2ae1ea1bd20835116304906169cb4d7d8737f25a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "91d11704d5fe4bcde56fa35fa6457d3b002ef561a7a433d16b393d6323068810", "generation_seconds_batch": 23.737628203001805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11535344272851944, "target_z": -0.255859371423947, "ce": 5.982900142669678, "genuineness": 4.645420074462891, "identity": 0.6934897303581238, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4c7e46af47ec68e973acebbf2ae1ea1bd20835116304906169cb4d7d8737f25a.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "4cc0e49de636fd60fe0183d021139f9926e9b0da470b657d15eff19247e320bf", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "940b843c6a394d97be2829ef59ed73df83fdd6a80c9c935ccd41989e6e99c765", "generation_seconds_batch": 25.09198809391819, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1336333453655243, "target_z": -0.21093751773722288, "ce": 6.205295085906982, "genuineness": 4.68307638168335, "identity": 0.7561044096946716, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4cc0e49de636fd60fe0183d021139f9926e9b0da470b657d15eff19247e320bf.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "4cd849df86e0438fcfacb85ede6cee8d004c8c76f656711625c7640fb2b07cf2", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "64a5bb3506111cdeea97b9f3f966e2eb1241ca8a223b11cf5bd3281c43a4b485", "generation_seconds_batch": 18.203911963966675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016800880432128906, "target_z": -0.49804686398575676, "ce": 6.41180419921875, "genuineness": 4.469690799713135, "identity": 0.6598436832427979, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4cd849df86e0438fcfacb85ede6cee8d004c8c76f656711625c7640fb2b07cf2.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "4ce779bc8519bacac70f508afae1ec7dd6468aedc122ef2dd8313877a9b691cd", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0de50c1fe56cc428d91d9a911cef0d0bbb57538bedf5fe8f3208c37d6fdf9a7c", "generation_seconds_batch": 23.84346440806985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15668193995952606, "target_z": -0.15429686627443068, "ce": 5.9431867599487305, "genuineness": 4.68307638168335, "identity": 0.5438663959503174, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4ce779bc8519bacac70f508afae1ec7dd6468aedc122ef2dd8313877a9b691cd.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": "4d0f3d627a48d076056d86569e7e4313b55f40d1bb9b4694c307f4688633266a", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ba99e65a74de9e35c49719a2a6e3bfb6fc812bc78f9d77bb65150a84edad2200", "generation_seconds_batch": 20.674130468978547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1368124783039093, "target_z": -0.20312497368024993, "ce": 6.23706579208374, "genuineness": 4.909013748168945, "identity": 0.6221007108688354, "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_Bitterness/4d0f3d627a48d076056d86569e7e4313b55f40d1bb9b4694c307f4688633266a.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": "4d1050392026c0de061860fa3705b66e06f87f50d1d280f763fd22a6e659aa3e", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af27d9800f8521556f2a1c0f3512710f3f6b188f5f34ef27882194bcfa9c010e", "generation_seconds_batch": 24.557670356007293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22980158030986786, "target_z": 0.02539062171003124, "ce": 5.911416053771973, "genuineness": 4.469690799713135, "identity": 0.1577039659023285, "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_Bitterness/4d1050392026c0de061860fa3705b66e06f87f50d1d280f763fd22a6e659aa3e.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "4d28ff52bfc9079a37ff2207f335941ad8f59caa4821fafbef2a2711fd394d42", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b045e012f06994b4da0885fab8e088bc7f207a909bee3dc471c64eb26e6fc1e3", "generation_seconds_batch": 22.398832016042434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16542449593544006, "target_z": -0.13281251659288593, "ce": 6.006728172302246, "genuineness": 4.2751336097717285, "identity": 0.24988287687301636, "hypothesis": "The 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_Bitterness/4d28ff52bfc9079a37ff2207f335941ad8f59caa4821fafbef2a2711fd394d42.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "4dfd03d4400b42b344a421d2f3cf7290967977b3dc35950de4b46a3cb4cb286a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7b7bdf752b81d2141273608980f17687ac5e5d6e834f29af2f6cf08cf74f9490", "generation_seconds_batch": 22.281622506910935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.033270180225372314, "target_z": -0.6210937371262092, "ce": 6.022613525390625, "genuineness": 4.645420074462891, "identity": 0.37533703446388245, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4dfd03d4400b42b344a421d2f3cf7290967977b3dc35950de4b46a3cb4cb286a.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "4e0c8cd09e77d0a09d7dbf93e87afb58a722649eeb0be54c9d8d1a031e7574ff", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "516fafbf07e40eb0af3108551aa1f47c283a059508182a584605c7aed779bedb", "generation_seconds_batch": 23.69153708999511, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1368124783039093, "target_z": -0.20312497368024993, "ce": 5.498397350311279, "genuineness": 4.369274139404297, "identity": 0.46706423163414, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4e0c8cd09e77d0a09d7dbf93e87afb58a722649eeb0be54c9d8d1a031e7574ff.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "4e2d47e36a368e81efa06f29c2084540b967b85a9aa5da1e4f25516e0e5b68e1", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "fa0c968140e0f09d8b708c1fdee7e6384bab5dc6c5b299693ee395be41337f68", "generation_seconds_batch": 21.42608519992791, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10184220224618912, "target_z": -0.2890625005721685, "ce": 5.935244083404541, "genuineness": 4.118232727050781, "identity": 0.45244961977005005, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4e2d47e36a368e81efa06f29c2084540b967b85a9aa5da1e4f25516e0e5b68e1.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "4e31d431a07a368f82b69666cb2d40cbbeb5a31660fe641174d2a24574ea75a0", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5c5cc3353cdd98353fb94443a0fe79ce9e49688f4121ca9cb9ecb142c6febbaa", "generation_seconds_batch": 23.369413670967333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24013370275497437, "target_z": 0.05078124342006248, "ce": 5.95112943649292, "genuineness": 4.68307638168335, "identity": 0.5776282548904419, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4e31d431a07a368f82b69666cb2d40cbbeb5a31660fe641174d2a24574ea75a0.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "4e6a799d7bc4210082214ea3bb276ecbfd74241dde39f4a00ec4120fa2e0968f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d47095cfe9b4c2b2dcbd1a04fbf7a183b3a335516f790b287112c9deef4dde80", "generation_seconds_batch": 25.347725435975008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028722554445266724, "target_z": -0.46875000686602175, "ce": 5.927301406860352, "genuineness": 4.65797233581543, "identity": 0.7340343594551086, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4e6a799d7bc4210082214ea3bb276ecbfd74241dde39f4a00ec4120fa2e0968f.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "4efd6258f65e02677a0b6537f5882710d9d836cdfbdb55904492f4a39126c52d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b11916d6c2898f280fa7ad6a7d902c2022e4d2d987855d8c108a077b6667e55d", "generation_seconds_batch": 24.205567545024678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22980158030986786, "target_z": 0.02539062171003124, "ce": 5.645336627960205, "genuineness": 4.268857479095459, "identity": 0.4186256229877472, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4efd6258f65e02677a0b6537f5882710d9d836cdfbdb55904492f4a39126c52d.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "4f0e264bf4a21fa164b160bcc30ebfc6e23822da81749d5bca528fc079d9e1a4", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9d6a66bace4defa4a5a13aa4db2e50153ffc8c27a9292f0e831d11ed9f066703", "generation_seconds_batch": 18.203911963966675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05733458697795868, "target_z": -0.398437513159875, "ce": 6.38003396987915, "genuineness": 4.557555198669434, "identity": 0.5894647836685181, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4f0e264bf4a21fa164b160bcc30ebfc6e23822da81749d5bca528fc079d9e1a4.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "4f1377f1b990237334f8dd94b56c0fbda19c17ae0fa860c4d4dc932e253626aa", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "3036f9de9f29e57e3348f2b457d3e62bc63e852569b46d41a63da678316fbc55", "generation_seconds_batch": 24.047341816942208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16621927917003632, "target_z": -0.1308593805786427, "ce": 5.681078910827637, "genuineness": 4.65797233581543, "identity": 0.7508351802825928, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4f1377f1b990237334f8dd94b56c0fbda19c17ae0fa860c4d4dc932e253626aa.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "4f716af864795514dc49c6368ab0b948939b0f07ff711fa1869fed9fd854f954", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "589a54d63255c8ac4e3c672c427c1e6745fc93933c9216eaa2362cbc8f6e79ba", "generation_seconds_batch": 24.29915293806698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1455550342798233, "target_z": -0.18164062399870515, "ce": 5.990842819213867, "genuineness": 4.909013748168945, "identity": 0.7289626002311707, "hypothesis": "La porte 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_Bitterness/4f716af864795514dc49c6368ab0b948939b0f07ff711fa1869fed9fd854f954.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "4fa628408acd34f563157313c8821da2be1cad1f1d814cef58aaf989c84b3bcc", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "288090075bbbb1ace927b9e3668c5672dae45360e0d23fd9b9e111569da74d63", "generation_seconds_batch": 26.771555451094173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09071530401706696, "target_z": -0.3164062399870516, "ce": 5.732706069946289, "genuineness": 4.369274139404297, "identity": 0.43683236837387085, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Wanneer je klaar bent.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4fa628408acd34f563157313c8821da2be1cad1f1d814cef58aaf989c84b3bcc.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "4fb1af12e8a0e5dfb84c814ae9345d76733a927b00e29dafcb9875d3fe18a62f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d5482df63eb08c027df3354d1824c2be9af41a8e89446d8b64e6130fb1d7b767", "generation_seconds_batch": 24.910094938008115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19642087817192078, "target_z": -0.05664061484400948, "ce": 5.617537498474121, "genuineness": 4.595211505889893, "identity": 0.5334994792938232, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/4fb1af12e8a0e5dfb84c814ae9345d76733a927b00e29dafcb9875d3fe18a62f.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "5001507ff1416aaf86b25fd79116e53615acaf415174c6bfa56bcbfea83ae8b3", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "673938e6073338492727d6c84ff333ffa18ec8f7dce95b2d98d322fbbcf4f881", "generation_seconds_batch": 22.400180338998325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05733458697795868, "target_z": -0.398437513159875, "ce": 6.38797664642334, "genuineness": 4.7332844734191895, "identity": 0.600639283657074, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/5001507ff1416aaf86b25fd79116e53615acaf415174c6bfa56bcbfea83ae8b3.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "50682959109c3c2cff4f913dff5b4f32dc131385c22ebe72d9c0e1cc1a596de2", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "12168bde07fe8f6f4d1f04538d3240e3d33b706b85cd33349267f6c0f5d0abfa", "generation_seconds_batch": 22.156160891987383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38478344678878784, "target_z": 0.4062500205980653, "ce": 6.054384231567383, "genuineness": 4.293961524963379, "identity": 0.42106205224990845, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/50682959109c3c2cff4f913dff5b4f32dc131385c22ebe72d9c0e1cc1a596de2.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "5266cd70a66ec925eedffbc6b1ef583f35e17575f2e629f7b8b1ce52a44b75d5", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c46f2118349258e5b6376f844cb8b3db4a1ff24500cdfec1a147d84e74adf26e", "generation_seconds_batch": 21.545055855996907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16383494436740875, "target_z": -0.13671875200258968, "ce": 6.09409761428833, "genuineness": 4.7081804275512695, "identity": 0.693834125995636, "hypothesis": "La porte 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_Bitterness/5266cd70a66ec925eedffbc6b1ef583f35e17575f2e629f7b8b1ce52a44b75d5.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "527eb51d298304dca50d4ef4ee0801eac540413215be590cc36c7ea5c7bf87c0", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "139f9937714b8312a4d9eb8aad4f7033295bb1ab3034c8ea90cfe2a0fcc766e7", "generation_seconds_batch": 23.684670781018212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0899205207824707, "target_z": -0.3183593760012948, "ce": 6.117925643920898, "genuineness": 4.595211505889893, "identity": 0.8294352293014526, "hypothesis": "La porte 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_Bitterness/527eb51d298304dca50d4ef4ee0801eac540413215be590cc36c7ea5c7bf87c0.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": "52d16b27ae680ad481b0cbf432a8a649baf77cfc170bacc96f6621d506aaffe1", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f3433a0d8217ccad7bcaf306e6f24387a4d58dbe930a238a531f76544ad0b78b", "generation_seconds_batch": 16.85415126301814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1837044060230255, "target_z": -0.08789064459677044, "ce": 6.054384231567383, "genuineness": 4.250029563903809, "identity": 0.24193590879440308, "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_Bitterness/52d16b27ae680ad481b0cbf432a8a649baf77cfc170bacc96f6621d506aaffe1.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "52e334dbe1b85f2412bd254d57ad75f38e1765bd3b7af1b8a245e5528d7ab446", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "847e955a850fec63ce7d9e81f528057f5c225ebbbfeb724aa658654431943bba", "generation_seconds_batch": 23.14082531898748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19006264209747314, "target_z": -0.07226562972038995, "ce": 5.808161735534668, "genuineness": 4.268857479095459, "identity": 0.4699873626232147, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/52e334dbe1b85f2412bd254d57ad75f38e1765bd3b7af1b8a245e5528d7ab446.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "52f2f95a752431f2ea87a87de51c07296592c442be9d131ab6e41913b1b70ce3", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f92e9824f9ddd9d6d2573a0cf25a365f86ab8c40c888c88920b6cb389a08d6f2", "generation_seconds_batch": 24.132053697947413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14476025104522705, "target_z": -0.18359376001294841, "ce": 5.974957466125488, "genuineness": 4.344170093536377, "identity": 0.32239362597465515, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/52f2f95a752431f2ea87a87de51c07296592c442be9d131ab6e41913b1b70ce3.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "52f8aa15860461a228d3ad907e15eac638d4ac316e3fb848b10b22ce3dd638a5", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9a8a119dfb9c68a40ec8dfb0b1a4fd7853b2bafbd580590f431f54d227ce3fe1", "generation_seconds_batch": 22.96614741103258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1614506095647812, "target_z": -0.14257812342653667, "ce": 5.184661865234375, "genuineness": 4.231201171875, "identity": 0.5860062837600708, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/52f8aa15860461a228d3ad907e15eac638d4ac316e3fb848b10b22ce3dd638a5.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "5331e857af2475ecb6e8f49b306cc3fda2e65e3f645152cd419ce28227e44c9b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c934762099df9f2b6b18e910cd3baa5a99b68894704b2d140701607f39c844b8", "generation_seconds_batch": 23.919414627016522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18529397249221802, "target_z": -0.08398437256828396, "ce": 5.808161735534668, "genuineness": 4.344170093536377, "identity": 0.23362191021442413, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/5331e857af2475ecb6e8f49b306cc3fda2e65e3f645152cd419ce28227e44c9b.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "534d548e15d7ae70bb6a40e42e609fac6ec1ae592514c8e399e672e0d343f4df", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4d9dea83f745dc68c00d0554a2ca45bc32f548afccc85a04b0c69d5d1c8bd16f", "generation_seconds_batch": 21.74320991395507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07640928030014038, "target_z": -0.3515625051495163, "ce": 5.967014789581299, "genuineness": 4.532451152801514, "identity": 0.671669602394104, "hypothesis": "La porte 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_Bitterness/534d548e15d7ae70bb6a40e42e609fac6ec1ae592514c8e399e672e0d343f4df.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "540cb19ffd06f42dbe8b6085dd46e904ade990e9b225069729183c8cb5bc55a9", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "bd080afd2d6932f6903f3d28e87f935f97a5199a023edfe9d9e61cc79270ceb2", "generation_seconds_batch": 26.375579490093514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13283857703208923, "target_z": -0.2128906171326834, "ce": 6.149696350097656, "genuineness": 4.306513786315918, "identity": 0.400917112827301, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/540cb19ffd06f42dbe8b6085dd46e904ade990e9b225069729183c8cb5bc55a9.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "5457fbdd1c0b78fea9ba1791787138abe011deb036edbec3151a182aa72a5e5a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6fa769691e407dafa53ef7ef788c9c77ab19969d0d7b5e991a08894539a5e124", "generation_seconds_batch": 22.80264844908379, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11853255331516266, "target_z": -0.24804688229514812, "ce": 6.332377910614014, "genuineness": 4.231201171875, "identity": 0.3143981397151947, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/5457fbdd1c0b78fea9ba1791787138abe011deb036edbec3151a182aa72a5e5a.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "f2c94934e77ad33abdbe466af2b0e0be75287ac60bce4e5fdd2df342915e2d9d", "generation_seconds_batch": 20.428783176932484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03905467689037323, "target_z": -0.44335938515599055, "ce": 6.300607204437256, "genuineness": 4.074300289154053, "identity": 0.557823896408081, "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_Bitterness/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "5536980dd619ecab1de0bab1ced119f9a285ceea1b9fbe023188ef583019e41e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "052698d37223f10296f6f8cf2e7d5e172d67090e004f5601fbfcca9c9f754329", "generation_seconds_batch": 23.383268150035292, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09071530401706696, "target_z": -0.3164062399870516, "ce": 6.38003396987915, "genuineness": 4.6956281661987305, "identity": 0.537104606628418, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/5536980dd619ecab1de0bab1ced119f9a285ceea1b9fbe023188ef583019e41e.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "5591c207706736cc69d13a93cb133a75f54af734c129ab5320f6860a8a1eb1fe", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9ffd9a4b2651bbbfdefcf5bb159fd58f7ffc0744a6468830945035cae5f77591", "generation_seconds_batch": 23.321505650063045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1074056550860405, "target_z": -0.27539062171003126, "ce": 6.23706579208374, "genuineness": 4.457139015197754, "identity": 0.1622430682182312, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/5591c207706736cc69d13a93cb133a75f54af734c129ab5320f6860a8a1eb1fe.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "55c984417b051bfd6f10560e7e7459921da4dce2a506fe127e943f2d4eabb274", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "eac4aee8e83aff5e0bca8031f2e61d097ed9110db5485b47dd3472d8b3d05a36", "generation_seconds_batch": 22.901264299987815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07481972873210907, "target_z": -0.35546874055922006, "ce": 6.0305562019348145, "genuineness": 4.909013748168945, "identity": 0.6702926158905029, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/55c984417b051bfd6f10560e7e7459921da4dce2a506fe127e943f2d4eabb274.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "56c20fae47cbab2a0b4c4bc9d79b45cef19627785e126f9409a2635ee0e739ab", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5dafc9371c9ea099dfbe7cfb1c043f38ea467ce1e7fac03dfc56f97c24ef352e", "generation_seconds_batch": 24.813790611107834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19006264209747314, "target_z": -0.07226562972038995, "ce": 6.165581703186035, "genuineness": 4.6203155517578125, "identity": 0.41112205386161804, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/56c20fae47cbab2a0b4c4bc9d79b45cef19627785e126f9409a2635ee0e739ab.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "57dcb86dd040e896013be98f59ec2a531baac35101d8e4ada4e93f7f85ab99ff", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b54746c3ef595a3442853118dfeed634f8916c36a8d93cfdaf54fe6a4631825e", "generation_seconds_batch": 20.246629150002263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035875558853149414, "target_z": -0.4511718925941808, "ce": 6.340320587158203, "genuineness": 4.162164688110352, "identity": 0.4661378264427185, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/57dcb86dd040e896013be98f59ec2a531baac35101d8e4ada4e93f7f85ab99ff.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "5887ad31403f71b4d8ea32c7d06b96f0996de9cc09b78efe4c92df52d9b70b95", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d0bd544b9067704373f013fe85e01cd132ec00a8ded24918ba62c3e616b508ac", "generation_seconds_batch": 17.040048383991234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08117794990539551, "target_z": -0.33984376230162233, "ce": 6.046441555023193, "genuineness": 4.68307638168335, "identity": 0.7134579420089722, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/5887ad31403f71b4d8ea32c7d06b96f0996de9cc09b78efe4c92df52d9b70b95.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "58d2a7b5c1f3d6591a561cb26fff3bde43fb0d0bc54e92eb7fca6f7e448f1f4f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "864a9de09d153ef714d4af9131f91e1d471dc8661c6be80ab0fdf3890af7f51c", "generation_seconds_batch": 27.091077251941897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1821148544549942, "target_z": -0.09179688000647421, "ce": 5.49045467376709, "genuineness": 4.174716949462891, "identity": 0.19047383964061737, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/58d2a7b5c1f3d6591a561cb26fff3bde43fb0d0bc54e92eb7fca6f7e448f1f4f.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": "58d9e1ebeeffe69dcec88f81a17bd0c2bbf4dee33d0656b3088834cbf6e7dfe0", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2b2cc0ad3a2db2cfd3c0f5a7c4807ae6b5bdd4be97970e4b5f9ed2047b100590", "generation_seconds_batch": 18.686993557028472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12091689556837082, "target_z": -0.24218749256180977, "ce": 5.935244083404541, "genuineness": 4.65797233581543, "identity": 0.5990660786628723, "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_Bitterness/58d9e1ebeeffe69dcec88f81a17bd0c2bbf4dee33d0656b3088834cbf6e7dfe0.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "58ebeb3a1e348c2fc094d3403565dc3340737b91b3d7f64e0ccc782ec10c714a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "43573bab6b3c28bca384768b29c4e17a7b3db2d4b460db4308f9092432a915c8", "generation_seconds_batch": 20.042053957935423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18608875572681427, "target_z": -0.08203123655404072, "ce": 5.224375247955322, "genuineness": 4.356721878051758, "identity": 0.40573421120643616, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/58ebeb3a1e348c2fc094d3403565dc3340737b91b3d7f64e0ccc782ec10c714a.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": "58fe53e6c766219f2e44e6857b760e4cd1cb50689ecd57c58103ff702ab92e66", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "35232b04e8a5965152dbecbf443d37be52942c248a69cc6c5654dd78f8858519", "generation_seconds_batch": 23.867935826070607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5151271820068359, "target_z": 0.726562569232386, "ce": 5.236289024353027, "genuineness": 4.218649387359619, "identity": 0.2567964494228363, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était d'ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/58fe53e6c766219f2e44e6857b760e4cd1cb50689ecd57c58103ff702ab92e66.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "591e2de8ccab04a61b0f4e4bb25d40bbdbc8ce526d414cd19ab01fbba692370f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "cf5dccaa1021830762062b7d4cb61529523e0723029989ede253f76ac010a696", "generation_seconds_batch": 24.738958352943882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08833096921443939, "target_z": -0.3222656114109986, "ce": 5.847874641418457, "genuineness": 4.262581825256348, "identity": 0.7887373566627502, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/591e2de8ccab04a61b0f4e4bb25d40bbdbc8ce526d414cd19ab01fbba692370f.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "595237c6bbe0b0805be58bd2612c78d038fa30fb3b3f4491865434e184fe6dd7", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a7ea3f6678a103224262761b67910bf2fc2b6495588eef37946d6eea9db44c65", "generation_seconds_batch": 17.77802512398921, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17257751524448395, "target_z": -0.1152343657022622, "ce": 6.054384231567383, "genuineness": 4.821148872375488, "identity": 0.8432579040527344, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/595237c6bbe0b0805be58bd2612c78d038fa30fb3b3f4491865434e184fe6dd7.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "59a9ee16032f6d283e35265f4a44146aff9ce3054e50eba3f2483e6401cff028", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6b55daaee89daa52b7f4c8e4dc81cc7876a267b252a60e29bdd4fb600c75785f", "generation_seconds_batch": 23.637818983988836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2834491431713104, "target_z": 0.15722655198640417, "ce": 5.3514580726623535, "genuineness": 4.168440818786621, "identity": 0.30152878165245056, "hypothesis": "De deur staat nog open. Ik heb een 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_Bitterness/59a9ee16032f6d283e35265f4a44146aff9ce3054e50eba3f2483e6401cff028.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "59af36095de593a6d9754fd3564dc5156ab1d94a5317e3a990d215e193fb7419", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "12dbf9b2e3d0a3634a2cf41b8d2a1453b8c141a09c4b20616b9d601b20bb4206", "generation_seconds_batch": 22.243028830038384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13283857703208923, "target_z": -0.2128906171326834, "ce": 6.229123115539551, "genuineness": 4.595211505889893, "identity": 0.4982524514198303, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/59af36095de593a6d9754fd3564dc5156ab1d94a5317e3a990d215e193fb7419.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "59db7597f49902ea40d9fb2951dd1b77991f6bc0bcf62d1e62fbafdfb7311a94", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e74ae770fbf0d0ae2cf94197210237462f21af661b542899ea15966a4f1c4dbf", "generation_seconds_batch": 16.875676800962538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14793936908245087, "target_z": -0.17578125257475816, "ce": 5.5738525390625, "genuineness": 4.545003414154053, "identity": 0.5656846761703491, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/59db7597f49902ea40d9fb2951dd1b77991f6bc0bcf62d1e62fbafdfb7311a94.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "5a079e842aeb3d85bcb6f4cc72dc6ffa1a71eca653aa4de59d2cc9491539bd82", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e64ec45492c89e2bec912fc6b267b4c07ab39971e352ef86e476dad0247d0937", "generation_seconds_batch": 24.478706346009858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11296910792589188, "target_z": -0.261718742847894, "ce": 6.173524379730225, "genuineness": 4.7081804275512695, "identity": 0.6665023565292358, "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_Bitterness/5a079e842aeb3d85bcb6f4cc72dc6ffa1a71eca653aa4de59d2cc9491539bd82.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "5a30f2b08cdf7e9196e88b993339a7c5cfa5383498b1e64dde918fc356c0f625", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4baed6e716cafedfb900b0a37ee7ad0814fbb95caff68be8e3ea1bf3f07b5879", "generation_seconds_batch": 16.875676800962538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25443971157073975, "target_z": 0.08593747196374447, "ce": 5.681078910827637, "genuineness": 4.482243061065674, "identity": 0.5815988779067993, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/5a30f2b08cdf7e9196e88b993339a7c5cfa5383498b1e64dde918fc356c0f625.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "5b15ca1e2d3a45310e71f8924dbde1d1374a80279cffc117a98e43d2dbed9745", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "621a3d30ff2338fa04e32a2092bbd1ac18e5f7a399a72ce68fe53dda65ac33b1", "generation_seconds_batch": 24.40575316408649, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1630401611328125, "target_z": -0.13867188801683292, "ce": 6.356205940246582, "genuineness": 4.519899368286133, "identity": 0.10839192569255829, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/5b15ca1e2d3a45310e71f8924dbde1d1374a80279cffc117a98e43d2dbed9745.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": "5bc79dea73b3f4e9a6a233bb63817eec540819f2711a72124ab5302ec87644b6", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Someone moved the little blue chair.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f57530fb6d27276e008d4f5f0e01569a2ab36e5b0e18d314f0aa41faea34a5fa", "generation_seconds_batch": 17.318436736939475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0899205207824707, "target_z": -0.3183593760012948, "ce": 6.507116317749023, "genuineness": 4.570107460021973, "identity": 0.307229608297348, "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_Bitterness/5bc79dea73b3f4e9a6a233bb63817eec540819f2711a72124ab5302ec87644b6.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": "5bf10ed7fd83f71b1d8000ee0c88b00b93033a9826acf8d39a12bc91ea809bd7", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d409eacb6d0560254ae5e27e71ec44f48e619ddcd45649c3393a5bcac5ef7c86", "generation_seconds_batch": 22.025799817987718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12489078938961029, "target_z": -0.23242186741876764, "ce": 5.959072113037109, "genuineness": 4.457139015197754, "identity": 0.7076770067214966, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las ze twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/5bf10ed7fd83f71b1d8000ee0c88b00b93033a9826acf8d39a12bc91ea809bd7.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "5d02166628e4856cfdc740072f512d9ee3996958001eaa3c527dce870ec4b4c5", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8f3ff53c4cf474ed9ad67ab587bfe2b6aff9787cc3558f8bf08b548c38f730bc", "generation_seconds_batch": 24.738958352943882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12489078938961029, "target_z": -0.23242186741876764, "ce": 6.0305562019348145, "genuineness": 4.482243061065674, "identity": 0.4610734283924103, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/5d02166628e4856cfdc740072f512d9ee3996958001eaa3c527dce870ec4b4c5.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "5da5a66d50800e3235ffa00adce108a91c9605364fcca737e2bfbbcaca974c59", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0b9c9eb6a407d9af11751865d91eea1abcaa96bd9a01fa0eaecb2fe8dddf5095", "generation_seconds_batch": 24.813790611107834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12409600615501404, "target_z": -0.23437500343301088, "ce": 6.284721851348877, "genuineness": 4.607763767242432, "identity": 0.5945374965667725, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/5da5a66d50800e3235ffa00adce108a91c9605364fcca737e2bfbbcaca974c59.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "8307cf2c2dcd475e8be79c9777c8ec972ee4e158c22c7cd48c602d958d6b4785", "generation_seconds_batch": 16.82806360803079, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15747672319412231, "target_z": -0.15234373026018744, "ce": 6.062326908111572, "genuineness": 4.369274139404297, "identity": 0.7843489050865173, "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_Bitterness/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "5e3a9a0188f8a4897da589ba0123212312184f19afcd09dc8d60d1078974fdef", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fc4b0f0819d3a06d82270959ad6c72d414ea2813982ab5e7df1d3a0994b2e20e", "generation_seconds_batch": 24.008186280960217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.001700073480606079, "target_z": -0.5351562651624647, "ce": 5.967014789581299, "genuineness": 4.18099308013916, "identity": 0.38868075609207153, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/5e3a9a0188f8a4897da589ba0123212312184f19afcd09dc8d60d1078974fdef.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": "5e4c3bc4b21a597304bab3a6001c3694a28bc9cba937e55ac57fb979b804990d", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "765531c72f44951d0d6c3e0d42fdd2598e2d098f95191e532a03a49336b7dfb6", "generation_seconds_batch": 21.28429691295605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17814096808433533, "target_z": -0.10156248684012496, "ce": 5.95112943649292, "genuineness": 4.369274139404297, "identity": 0.6911977529525757, "hypothesis": "De sleutels liggen op de keukentafel en keek in de la. En de naan als 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_Bitterness/5e4c3bc4b21a597304bab3a6001c3694a28bc9cba937e55ac57fb979b804990d.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": "5e69d87e6c125839d8a76f51eb0416f1ee454406ac3a050e6202d93ec3a9783d", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "457656881d27c643502412b6f61981041e96aafba148a3be8b0947da3ec69b5e", "generation_seconds_batch": 24.236544721992686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21072688698768616, "target_z": -0.021484386300327483, "ce": 6.070269584655762, "genuineness": 4.507347106933594, "identity": 0.46065032482147217, "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_Bitterness/5e69d87e6c125839d8a76f51eb0416f1ee454406ac3a050e6202d93ec3a9783d.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "5ef845555b98184aa3d7b1cebfadeeade9dc9c7065c14870e2b67bf02b05c829", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d6c6fdeee4d09e15ead50bf8ee56b5e87eea676c9c9fc3277c257a7a8357a8d3", "generation_seconds_batch": 26.005073564010672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5850676894187927, "target_z": 0.8984375131598751, "ce": 5.244231700897217, "genuineness": 3.936227321624756, "identity": 0.24892282485961914, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/5ef845555b98184aa3d7b1cebfadeeade9dc9c7065c14870e2b67bf02b05c829.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "5f098d9daf98b6b27acefc9c86df16f812eb4cfc54dc7929bfb6022e0bfa9aae", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "614be32b9f4850226fc2cc52a6f233baf179f83275144681129b6235d9decf16", "generation_seconds_batch": 24.29225800500717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06130848824977875, "target_z": -0.38867186970744155, "ce": 5.732706069946289, "genuineness": 4.557555198669434, "identity": 0.7281609773635864, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/5f098d9daf98b6b27acefc9c86df16f812eb4cfc54dc7929bfb6022e0bfa9aae.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "5fa26d4ae2c5f588fba93ff770836cc0fa43e58cb7392c22e69dfedb3e7b9bcc", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fe5fb09727aa04055f24b0bac76303450d556f8262786154d129d5d536d98de1", "generation_seconds_batch": 24.373580323066562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10661087185144424, "target_z": -0.2773437577242745, "ce": 5.895530700683594, "genuineness": 4.758388519287109, "identity": 0.7675991654396057, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/5fa26d4ae2c5f588fba93ff770836cc0fa43e58cb7392c22e69dfedb3e7b9bcc.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "603a6a149f9fb6d6056f586b1517c2095ae2b8c41614e04c5f9fcb0ab8c69664", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "45a425a601546ede1805e5bdfbe3702ec4b4737adcbfbb9ee50c55dd153939ca", "generation_seconds_batch": 31.832273195963353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10978998988866806, "target_z": -0.26953125028608427, "ce": 5.935244083404541, "genuineness": 4.570107460021973, "identity": 0.6315596103668213, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/603a6a149f9fb6d6056f586b1517c2095ae2b8c41614e04c5f9fcb0ab8c69664.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "604730e329d2b3d5f85d982bf6495dbe2b461dbf046f7c822d5ef74c3a087f34", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "87023b0fdb718c02b26aa209da0a7f79f6e782da4e7349ec094f3c3394520bdd", "generation_seconds_batch": 22.567030510981567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.117737777531147, "target_z": -0.25, "ce": 5.808161735534668, "genuineness": 4.65797233581543, "identity": 0.601662814617157, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/604730e329d2b3d5f85d982bf6495dbe2b461dbf046f7c822d5ef74c3a087f34.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "6085311da0ced9f51c82ae8ebbee4568fa09cc3c1090ec4b5b954c1059d10ba3", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bd2e36c06e77319c5ad22c3966f8eee32bccf864c62af4e0e4bcd2ec9c7bd8a0", "generation_seconds_batch": 24.913341960054822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13204379379749298, "target_z": -0.21484375314692664, "ce": 6.24500846862793, "genuineness": 4.532451152801514, "identity": 0.6115281581878662, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/6085311da0ced9f51c82ae8ebbee4568fa09cc3c1090ec4b5b954c1059d10ba3.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "60dd187d85644776001e6ab8311a56dbe4052c222411f7460285c733146c8015", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4e3de4f7ab0967e311d164b58f42ebf637e9ffec755818209b0e75cb7d5873c8", "generation_seconds_batch": 22.9438432760071, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07561449706554413, "target_z": -0.35351564116375955, "ce": 5.8875885009765625, "genuineness": 4.582659721374512, "identity": 0.8158411383628845, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/60dd187d85644776001e6ab8311a56dbe4052c222411f7460285c733146c8015.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "6141d72b72f51e6b88812c2821af4cb465e01dc691aa28fd30e21e0a78817884", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7bf1bfc0c97b40db9da7d72ece21efc495d08b2ce4cedd82b95c8c5ddb7e6fa1", "generation_seconds_batch": 24.38816361106001, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.164629727602005, "target_z": -0.13476561598834644, "ce": 5.093321323394775, "genuineness": 4.331617832183838, "identity": 0.580982506275177, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/6141d72b72f51e6b88812c2821af4cb465e01dc691aa28fd30e21e0a78817884.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "61b265f994da27542a9627474bd5670f2af6e824c768414ffdee67b27a14c7bf", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "899aa24c32a13e7bc6ed7ed8f1a56d5063c4f8af20f734d8300769017cc807d5", "generation_seconds_batch": 22.881412907969207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14476025104522705, "target_z": -0.18359376001294841, "ce": 5.331601142883301, "genuineness": 4.394378662109375, "identity": 0.8241115212440491, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/61b265f994da27542a9627474bd5670f2af6e824c768414ffdee67b27a14c7bf.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "61b90baac30aa0de30ac87921c35a7e3671c0f2fe65631528bf76ee129cf84e5", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2a74cdfbce23768e013b955ee271f96b240eb4dbc6680d1adf89dbac8afbd26d", "generation_seconds_batch": 25.426297956029885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05711355805397034, "target_z": -0.6796875246032447, "ce": 6.284721851348877, "genuineness": 4.645420074462891, "identity": 0.48830974102020264, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/61b90baac30aa0de30ac87921c35a7e3671c0f2fe65631528bf76ee129cf84e5.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "6236f7848f9be7eb0a38ea78e7ac39080af36c149dbe15ed13f5b5ab60dd1341", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "35496f49e930690d05a856bcd2d79dfa94c92bd0bd96e6c07502db36050aab2c", "generation_seconds_batch": 18.416059608920477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17416706681251526, "target_z": -0.11132813029255845, "ce": 5.692992687225342, "genuineness": 4.582659721374512, "identity": 0.8029531836509705, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la de la vie 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_Bitterness/6236f7848f9be7eb0a38ea78e7ac39080af36c149dbe15ed13f5b5ab60dd1341.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "63300dfdf77d0a4cf4d368509cdee0deb44fde19b7e51916caa8ef2c4729b8d2", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7059f7600fa6fcebf586ccfa6c3e896ba3611c6b6dbd057a59ac7ac27214a4e3", "generation_seconds_batch": 24.760904751019552, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8107848167419434, "target_z": 1.4531249187520758, "ce": 5.804190158843994, "genuineness": 4.080576419830322, "identity": 0.42537298798561096, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/63300dfdf77d0a4cf4d368509cdee0deb44fde19b7e51916caa8ef2c4729b8d2.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "641ea5b3698c4e3d6657b906f849cb95bd8a55925104a9935396a7cda224b05e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9daa2ab7788315dc5d9b33472bf1157398d269ee96d8d2b32de1499c92a6c069", "generation_seconds_batch": 28.662083862931468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17019318044185638, "target_z": -0.1210937371262092, "ce": 5.673136234283447, "genuineness": 4.268857479095459, "identity": 0.3665611445903778, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/641ea5b3698c4e3d6657b906f849cb95bd8a55925104a9935396a7cda224b05e.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "6462a377787e7a57ade186042cc8eb20fb543934085fa078d93e072c536db665", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a3e0db83e3cb39207cae09cbb71eed511f16e35d8a9e3cbbee6d376171cfaae8", "generation_seconds_batch": 24.12783022900112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014416545629501343, "target_z": -0.5039062354097038, "ce": 6.348263263702393, "genuineness": 4.168440818786621, "identity": 0.46983546018600464, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/6462a377787e7a57ade186042cc8eb20fb543934085fa078d93e072c536db665.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "64f01a7f48359b4c0adf8885a7d1487f9333a8ed8066ee91d3ec8e3421be7756", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0b4a60e3f6fa95452c60322fe5ffd0fe68de2eea5d1e18a0bf8667614e05e9e8", "generation_seconds_batch": 15.509391902014613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1352229118347168, "target_z": -0.2070312457087364, "ce": 6.213237762451172, "genuineness": 4.770940780639648, "identity": 0.7448634505271912, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/64f01a7f48359b4c0adf8885a7d1487f9333a8ed8066ee91d3ec8e3421be7756.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "65204b6021fbba9830c48b71fa2bfb8af85e5cbb9db7345aec0a81cede923bf8", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "419c31918b7169000059a969269dd2bffdf2a73d3d67acc96eb2366f461fda32", "generation_seconds_batch": 17.087452477077022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13124901056289673, "target_z": -0.21679688916116988, "ce": 6.054384231567383, "genuineness": 4.7458367347717285, "identity": 0.7602992057800293, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/65204b6021fbba9830c48b71fa2bfb8af85e5cbb9db7345aec0a81cede923bf8.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "657a02e2c9ef8e960c5120cfedc6588c67a8e2bb2db6540b686a04c070311836", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "821e0f8bef432ba2f87e477e300a90872fb56a48ce6601d20de8a6ba7bcc5269", "generation_seconds_batch": 23.049984700977802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2099321186542511, "target_z": -0.023437485695787998, "ce": 5.847874641418457, "genuineness": 4.595211505889893, "identity": 0.546718955039978, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/657a02e2c9ef8e960c5120cfedc6588c67a8e2bb2db6540b686a04c070311836.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "65939421892ae90c7a9dd886da4ca950aae54fb7b83fd0c9c7e647b50308f6bc", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "65fe1de963811cf88a7c63df170a2bb7646b202146b5fd36adb5b0838130af0d", "generation_seconds_batch": 21.704922662000172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.070845827460289, "target_z": -0.36523438401165353, "ce": 6.086154937744141, "genuineness": 4.331617832183838, "identity": 0.7517679929733276, "hypothesis": "La porte 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_Bitterness/65939421892ae90c7a9dd886da4ca950aae54fb7b83fd0c9c7e647b50308f6bc.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "66aed529faa3aca8fb599b72a37b1ae1d7adadce135e6c36f1c6510d0bfcb808", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b0dd41b96f8e1f764e9f94c93dc725c3ce200d0b309079842be98a4802bc3edf", "generation_seconds_batch": 23.241756162955426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11137954890727997, "target_z": -0.2656249965669891, "ce": 6.205295085906982, "genuineness": 4.833701133728027, "identity": 0.7369858026504517, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/66aed529faa3aca8fb599b72a37b1ae1d7adadce135e6c36f1c6510d0bfcb808.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "673577092094527cb50328e736879d6629bf4b8c2357bc859939845292046162", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c4e5566a2bf782b558be229efceec365502d3532ebcdf892d7c3949ad60f3b48", "generation_seconds_batch": 23.13287362002302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14317069947719574, "target_z": -0.18749999542265217, "ce": 5.6413655281066895, "genuineness": 4.3504462242126465, "identity": 0.3386737108230591, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/673577092094527cb50328e736879d6629bf4b8c2357bc859939845292046162.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": "67a1d683b7c0436148a4b284c84955ff62caa73eaa38f84e623e71bddfd160e7", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "77a024f38e91808d98a8e4e3c7bafcae6d8a0b4fc2a08cefa7f69d4c16d1b55a", "generation_seconds_batch": 16.566019571968354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29417866468429565, "target_z": 0.18359376001294841, "ce": 6.078212261199951, "genuineness": 4.545003414154053, "identity": 0.7642108201980591, "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_Bitterness/67a1d683b7c0436148a4b284c84955ff62caa73eaa38f84e623e71bddfd160e7.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "67ec4899e5b09f65c56c85d2781ff881f851e321aa611bb271af8a95c7840120", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3e3e8620583ffeff1b8d344e7eaf6cc9c54a9f5ad7733572b1049af3e48c133e", "generation_seconds_batch": 22.281622506910935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07640928030014038, "target_z": -0.3515625051495163, "ce": 5.9431867599487305, "genuineness": 4.400654315948486, "identity": 0.1382870078086853, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/67ec4899e5b09f65c56c85d2781ff881f851e321aa611bb271af8a95c7840120.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "67ecf7bc36ac3fa6fe3781975605b0986d34e1a600d4bcfc43416ab9bd81570c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "96b6c99364c4e0744bf0dacf08e5c51aacd1d7c268e402db8e2094b7d2ad2fd6", "generation_seconds_batch": 23.30501281004399, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09627874940633774, "target_z": -0.3027343794343057, "ce": 6.109982967376709, "genuineness": 4.287685871124268, "identity": 0.09905394166707993, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/67ecf7bc36ac3fa6fe3781975605b0986d34e1a600d4bcfc43416ab9bd81570c.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "68d8591c6c547291b1edcc37e1e10400b2cbb85f2599d77fa9d39bec17fb3643", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "59f1eb0badf793cab4c7c30a664bed3c303e29127b667f61b2159dba43fc3979", "generation_seconds_batch": 24.29225800500717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08276751637458801, "target_z": -0.33593749027313585, "ce": 5.879645347595215, "genuineness": 4.68307638168335, "identity": 0.808538556098938, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/68d8591c6c547291b1edcc37e1e10400b2cbb85f2599d77fa9d39bec17fb3643.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": "69a889597217bb0a3f0ae5691e1aea5a126262226e680b856b5e5b8d6eb490b8", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ed052a5441a51f10c22485a7cb245388ed9b9fc77bf92eb15e440b4e21ce5d6f", "generation_seconds_batch": 23.867935826070607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15827149152755737, "target_z": -0.15039063086472693, "ce": 5.967014789581299, "genuineness": 4.720732688903809, "identity": 0.6728599667549133, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/69a889597217bb0a3f0ae5691e1aea5a126262226e680b856b5e5b8d6eb490b8.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "69ecda2a7e435c5e5d576f3b6190fc6d14f36efed03e71f77d387602089af963", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b12d04c3fdaaa1cd28fda8429397e90b759cd3f357a8c5c4125f26ce9cca8fee", "generation_seconds_batch": 28.305341074010357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07799884676933289, "target_z": -0.34765623312102983, "ce": 6.165581703186035, "genuineness": 4.570107460021973, "identity": 0.6088714599609375, "hypothesis": "Ma 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_Bitterness/69ecda2a7e435c5e5d576f3b6190fc6d14f36efed03e71f77d387602089af963.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "6a5d8d82c679e5b925e15d656de7da394144ad76575dda1737b5298ca4246331", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "15cc94f6a24ffa0c28a51b7b7512d5c96a1b14432cbb6628724adfdc4dc8e687", "generation_seconds_batch": 16.28955731203314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09627874940633774, "target_z": -0.3027343794343057, "ce": 5.510311126708984, "genuineness": 4.582659721374512, "identity": 0.5590710639953613, "hypothesis": "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_Bitterness/6a5d8d82c679e5b925e15d656de7da394144ad76575dda1737b5298ca4246331.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "cfbb31f9d4372829b72bfc15b3d00a095d5c480798f5ebb58d2fd6548b61ac9f", "generation_seconds_batch": 17.925391880911775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08435706794261932, "target_z": -0.3320312548634321, "ce": 6.459460258483887, "genuineness": 4.099404335021973, "identity": 0.3945089876651764, "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_Bitterness/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "8e13c9a284d3329d6695d93399517fc79d696363fec1f4680bd44987850b9486", "generation_seconds_batch": 17.561696356046014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11853255331516266, "target_z": -0.24804688229514812, "ce": 6.24500846862793, "genuineness": 4.6203155517578125, "identity": 0.6488242745399475, "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_Bitterness/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.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": "6b9f5d3ef67fc56e7949262bc1d3f0ccf6571186cd8e0b33aa84d6afc7fbe8ef", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9a43627814b13194b63163acc4ba132851c417bf2312042cc19a4581a015cf38", "generation_seconds_batch": 21.96685098297894, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1614506095647812, "target_z": -0.14257812342653667, "ce": 6.09409761428833, "genuineness": 4.65797233581543, "identity": 0.7207645177841187, "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_Bitterness/6b9f5d3ef67fc56e7949262bc1d3f0ccf6571186cd8e0b33aa84d6afc7fbe8ef.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "6c7604a0a50ac920a10dc1ed37a2e8fda4cf122905edc19883bf94196db8a79f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0e5a32bd450a5ed6d8eba9163da193648701fcaeb16dda6cd9209ee0827dd166", "generation_seconds_batch": 23.551090560969897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1749618500471115, "target_z": -0.1093749942783152, "ce": 4.6981730461120605, "genuineness": 4.13078498840332, "identity": 0.5576014518737793, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/6c7604a0a50ac920a10dc1ed37a2e8fda4cf122905edc19883bf94196db8a79f.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "6c865ed3a1f728e1c71e087be773bfce711be1d9c8c6e8b24843e4630d4fc564", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f794b521e87c42a28d3f0dc87ea4f417d4864f87e4496474c3ac64ffbd0e5d4e", "generation_seconds_batch": 17.035305746947415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20039476454257965, "target_z": -0.046875008010358724, "ce": 5.4944257736206055, "genuineness": 4.118232727050781, "identity": 0.6481021046638489, "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_Bitterness/6c865ed3a1f728e1c71e087be773bfce711be1d9c8c6e8b24843e4630d4fc564.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "6cbb499faeb2fe4db211d6ce9ac3454b8ecfc4e0a622ee03a37740d61212048f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d358946d7d3b83d8c3ead603d7a5cababd00edb8e4f8c06ebbe0cca6798bb9e6", "generation_seconds_batch": 17.47609936702065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11137954890727997, "target_z": -0.2656249965669891, "ce": 5.585766792297363, "genuineness": 4.356721878051758, "identity": 0.7342932820320129, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/6cbb499faeb2fe4db211d6ce9ac3454b8ecfc4e0a622ee03a37740d61212048f.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "6cc6c1589aff8f2b8671d0005e995f2eef44537816970fa114ea5b6e866c584d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "19bf2dee6e8b8eb49fe70877e29171ca864ee84e0be6611069b36541f8e645cd", "generation_seconds_batch": 23.279515890055336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018390432000160217, "target_z": -0.494140628576053, "ce": 6.395919322967529, "genuineness": 4.18726921081543, "identity": 0.6246127486228943, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/6cc6c1589aff8f2b8671d0005e995f2eef44537816970fa114ea5b6e866c584d.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "6d145c0652cad4c57ed3dbc2a02b1e4fa06b165367759b9b22eb134ea12bbf39", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3ab461cffd76f204d200a559d1c433983fbed19e0512c9b7aa346c04c00a33d6", "generation_seconds_batch": 28.749804561957717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11217432469129562, "target_z": -0.2636718788621372, "ce": 6.022613525390625, "genuineness": 4.7332844734191895, "identity": 0.5740931034088135, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/6d145c0652cad4c57ed3dbc2a02b1e4fa06b165367759b9b22eb134ea12bbf39.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "6db399351256ef1b3320a64f3819ddbe46089fa836ccfeb7dee046cc17670a0e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d3f7d97f17064028770ed4c6ee7a958d825b76ef126420cce40fb9fde27f5a7c", "generation_seconds_batch": 22.884328222018667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11694300174713135, "target_z": -0.2519531177048519, "ce": 5.1926045417785645, "genuineness": 4.369274139404297, "identity": 0.560795783996582, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/6db399351256ef1b3320a64f3819ddbe46089fa836ccfeb7dee046cc17670a0e.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "6db7fc232da675e61c3db40623a62c9a5d2c5e26faafe86b6f5d5a557b5aec7a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "bca614ea905126b7588e07ca9127b64ea683bbc7248001a8cbae74f01de97c49", "generation_seconds_batch": 22.20074590703007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19165220856666565, "target_z": -0.06835935769190347, "ce": 5.927301406860352, "genuineness": 4.425758361816406, "identity": 0.49018439650535583, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/6db7fc232da675e61c3db40623a62c9a5d2c5e26faafe86b6f5d5a557b5aec7a.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "6dc093c11d870c0ebccefdd2ed4a98419812e6d1c2832beab378183d65014b1a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "be93139ac59bb71bfe20dc25a295ca0940d48a3e9ed9810bc66e7d36f322b54d", "generation_seconds_batch": 22.87148223305121, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06528237462043762, "target_z": -0.3789062628737908, "ce": 6.300607204437256, "genuineness": 4.532451152801514, "identity": 0.5969789624214172, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/6dc093c11d870c0ebccefdd2ed4a98419812e6d1c2832beab378183d65014b1a.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "6e099748060d35be654a3f2614384964424e443b3bc183d796f0865c5332adb2", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b01e80983f3de2c09ee7c0f5a4d9d07ba0c84b2be0577fb9c6aefe62c82a2482", "generation_seconds_batch": 25.34052395890467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07799884676933289, "target_z": -0.34765623312102983, "ce": 6.252951145172119, "genuineness": 4.65797233581543, "identity": 0.32027167081832886, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/6e099748060d35be654a3f2614384964424e443b3bc183d796f0865c5332adb2.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "6e1c7e76ac95c7a420e4a4bc5f5f43fff5b9b2a38900ba6fb9694fb961aec44b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e402868538fa7d4f52a44e6c6b7610d3bcf32710f14acedb6cff87ba5ac06cea", "generation_seconds_batch": 24.591268897987902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11694300174713135, "target_z": -0.2519531177048519, "ce": 6.141753673553467, "genuineness": 4.306513786315918, "identity": 0.6473234295845032, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/6e1c7e76ac95c7a420e4a4bc5f5f43fff5b9b2a38900ba6fb9694fb961aec44b.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": "6eeec4389e0b6cc346f6bf71d4d2219a23388e390db8cd0e0ae5d20514714f45", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f867a2eafc738de736ce6d592c6507c269bd5321d7240d5202d4ff09d3ff6d6d", "generation_seconds_batch": 18.41936960304156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18608875572681427, "target_z": -0.08203123655404072, "ce": 6.046441555023193, "genuineness": 4.645420074462891, "identity": 0.7189218401908875, "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_Bitterness/6eeec4389e0b6cc346f6bf71d4d2219a23388e390db8cd0e0ae5d20514714f45.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "6f7cbac82a53280ed4f783edd2c7639a6a57ab31d2f1bc24058bd13d93f448e9", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bdb54f6291f062bf2251e6af98a45f22f4a9b266e5a494c783b0077a2b22ceb9", "generation_seconds_batch": 18.491830673068762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.117737777531147, "target_z": -0.25, "ce": 6.181467056274414, "genuineness": 4.507347106933594, "identity": 0.3497712016105652, "hypothesis": "Ik heb het een kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/6f7cbac82a53280ed4f783edd2c7639a6a57ab31d2f1bc24058bd13d93f448e9.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": "6f8cce73924e686e9373862d488945394eb5405409aea6ac27a89d731dba5947", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "01e181c2f5a4fe9b719fb0f6c086e5d2a0b14510a118a3902623d02f59d3ae16", "generation_seconds_batch": 20.789215727942064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15111848711967468, "target_z": -0.16796874513656793, "ce": 5.728734970092773, "genuineness": 4.457139015197754, "identity": 0.767600417137146, "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_Bitterness/6f8cce73924e686e9373862d488945394eb5405409aea6ac27a89d731dba5947.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "6f9220c4a3d6a33c550ca5ca5d3f94a6fc4789c0ea473d89b3d13a1e60a79448", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a15d1470c99cc219ce45a2ed5481603b43f23b7a8b5ecdafe2e57244d42e9ce9", "generation_seconds_batch": 25.60686301300302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03905467689037323, "target_z": -0.44335938515599055, "ce": 6.205295085906982, "genuineness": 4.425758361816406, "identity": 0.27942657470703125, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/6f9220c4a3d6a33c550ca5ca5d3f94a6fc4789c0ea473d89b3d13a1e60a79448.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "70124cdcf6772b1434de72a9c830691ee013b30ea86e74c6a2d72fffd589923d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "55246ac71fa96d24e73f64d19dac279f252146a1e01b3f7ba0ee71070a79fa53", "generation_seconds_batch": 21.3093351299176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07402494549751282, "target_z": -0.3574218765734633, "ce": 5.728734970092773, "genuineness": 4.243753433227539, "identity": 0.17146611213684082, "hypothesis": "I found the little box. It was beside the old window. What 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_Bitterness/70124cdcf6772b1434de72a9c830691ee013b30ea86e74c6a2d72fffd589923d.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "707751c37f1db1cd728c981c47d9ae8e849c127eb39532f88c0fccf48b234c78", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4e6ec2921c4356f24f9f1103e66ad4b9c06665159b5765241a0301ef11a39495", "generation_seconds_batch": 18.405122285941616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03746512532234192, "target_z": -0.4472656205656943, "ce": 6.213237762451172, "genuineness": 4.093128204345703, "identity": 0.3190716505050659, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/707751c37f1db1cd728c981c47d9ae8e849c127eb39532f88c0fccf48b234c78.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "708a78a5957585acba813bbca6df2c7ce735e5980b9b1a31abb5821d8edaf15c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "88e9c1cbbfc183e22d79d30c87124e5d562fa6c9164f6754fcbec5d02e9e5f27", "generation_seconds_batch": 22.9438432760071, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06766670942306519, "target_z": -0.3730468914498438, "ce": 6.229123115539551, "genuineness": 4.507347106933594, "identity": 0.6382855176925659, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/708a78a5957585acba813bbca6df2c7ce735e5980b9b1a31abb5821d8edaf15c.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "709a05a9c34d3fcb246d8fb6bd168ec0eda4453743fcf5110df9b2532f43c557", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4970614b08490deb127f547bc541cbb81def4306b8ed4be7b6f942848281fe45", "generation_seconds_batch": 21.42608519992791, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25046584010124207, "target_z": 0.07617190174887645, "ce": 6.117925643920898, "genuineness": 4.381826400756836, "identity": 0.744995653629303, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/709a05a9c34d3fcb246d8fb6bd168ec0eda4453743fcf5110df9b2532f43c557.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": "71077477427040ebd5b72716240bbf100410a1189f49221a581d3d78d85fcad2", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7215896084cba3e170043f6e0af1d96a17dd2bc1b1273af40171ccdcba1c580e", "generation_seconds_batch": 24.02683769899886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08197273313999176, "target_z": -0.3378906262873791, "ce": 6.078212261199951, "genuineness": 4.337893962860107, "identity": 0.4868183732032776, "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_Bitterness/71077477427040ebd5b72716240bbf100410a1189f49221a581d3d78d85fcad2.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "7114bb410201fe8e5f2a18cd8fb9fdcd2ec08ff0dcc1b9492b83ea34eb660ad2", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "94c835c48eb5023bd4742a5ff24e99bed96a85e0cc0b77859ee201c166ac382d", "generation_seconds_batch": 22.398832016042434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16701406240463257, "target_z": -0.12890624456439945, "ce": 6.054384231567383, "genuineness": 4.356721878051758, "identity": 0.29813748598098755, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7114bb410201fe8e5f2a18cd8fb9fdcd2ec08ff0dcc1b9492b83ea34eb660ad2.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": "71a609dd547e0fe5b709133abf6592c52f297ea26c4d415c2b11ead6039f3ad7", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ad9ab84f5f4bb510f136792ad10359000a543e368fed31fe71a62405e32b76f6", "generation_seconds_batch": 23.34040217893198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2274172455072403, "target_z": 0.01953125028608424, "ce": 5.998785495758057, "genuineness": 4.68307638168335, "identity": 0.49663689732551575, "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_Bitterness/71a609dd547e0fe5b709133abf6592c52f297ea26c4d415c2b11ead6039f3ad7.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": "7284dd6eb46c924421b1c69737c17481bda4753e7edbf20598eac3a22c11b66b", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f32f20da1000d893d88124a55cebbfd6a2e78c820d6268d08fea38572b83c8ba", "generation_seconds_batch": 16.73767429997679, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1908574253320694, "target_z": -0.07031249370614671, "ce": 6.141753673553467, "genuineness": 4.319066047668457, "identity": 0.7170171737670898, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekkast. We zetten het na de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7284dd6eb46c924421b1c69737c17481bda4753e7edbf20598eac3a22c11b66b.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": "734254fa72c44236af1c9b15fa06743478454a2fcef20030a7ae752a96bdf85b", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d6cdac5c2ed1042e776573a1b6ede6d90066d642d920b6ecf24d898d39846242", "generation_seconds_batch": 22.829724543960765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15509238839149475, "target_z": -0.15820310168413443, "ce": 5.95112943649292, "genuineness": 4.7332844734191895, "identity": 0.7642665505409241, "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_Bitterness/734254fa72c44236af1c9b15fa06743478454a2fcef20030a7ae752a96bdf85b.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "73550df458bce5686d09c8e85576b2b96030507ca06696e37050d8c1539e7dd9", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3218997a34ddc0944ee017019f6e2f299a907ba3791bfaede2e9081170bf2d6d", "generation_seconds_batch": 22.995358198997565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006247714161872864, "target_z": -0.554687515448549, "ce": 6.086154937744141, "genuineness": 4.293961524963379, "identity": 0.7076948285102844, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/73550df458bce5686d09c8e85576b2b96030507ca06696e37050d8c1539e7dd9.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "7371b9688dbcd9dc2e4dc5c1d481c7f18c6649bdb4327bff7e8d705cd5d10f49", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "93f086c4e1b2f077ddc511ee37469ef6b6d93d35c0650d313a1305126bc4a8aa", "generation_seconds_batch": 24.980551181011833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.018964171409606934, "target_z": -0.5859375085825272, "ce": 6.38003396987915, "genuineness": 4.7332844734191895, "identity": 0.4008488655090332, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7371b9688dbcd9dc2e4dc5c1d481c7f18c6649bdb4327bff7e8d705cd5d10f49.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "741dfa879d9013db94aeac105ffe57ae6eaa5b55bda662c096f1bcbca557f37e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8b293dc5bbca170832844aed4f130f30a5591c068dc41661b342059030494bdc", "generation_seconds_batch": 15.904753869050182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03190167248249054, "target_z": -0.4609374994278315, "ce": 6.292664527893066, "genuineness": 4.7834930419921875, "identity": 0.3690626621246338, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/741dfa879d9013db94aeac105ffe57ae6eaa5b55bda662c096f1bcbca557f37e.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "74b591d0fc0f7c3cd569d253fcbab440cfdf1c1105d153ce056e120efc378a1a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8a567b03d87f100181dc5319834b96ba59e027ebf69718a5643841cc01918982", "generation_seconds_batch": 23.482123175053857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1630401611328125, "target_z": -0.13867188801683292, "ce": 5.847874641418457, "genuineness": 4.6956281661987305, "identity": 0.7615111470222473, "hypothesis": "La porte 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_Bitterness/74b591d0fc0f7c3cd569d253fcbab440cfdf1c1105d153ce056e120efc378a1a.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "750f56e935e0328fa88d3da5aead61f888117173de8563b7335da6083207f8cd", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c3edd0247dca78ca32086d9b7e19211577ebf071dd2bd6c75251f5355850fa23", "generation_seconds_batch": 23.85233663499821, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20436866581439972, "target_z": -0.03710936455792524, "ce": 5.784333229064941, "genuineness": 4.256305694580078, "identity": 0.37219250202178955, "hypothesis": "Ik heb een kleine doosje gevonden, stond naast het oude raam. We kunnen samen inkijken.", "wer": 0.2777777777777778, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/750f56e935e0328fa88d3da5aead61f888117173de8563b7335da6083207f8cd.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "75370844e9c142efb6120ee67235d1dd5b68a1d34d942daf2981f0ccc836fd73", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4b6a3be63ae4a25af6dc2d731d40dbe13bc10757680fe4cd09fd357c2f2089a7", "generation_seconds_batch": 22.605092879966833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17734618484973907, "target_z": -0.1035156228543682, "ce": 5.3792572021484375, "genuineness": 4.507347106933594, "identity": 0.1356915384531021, "hypothesis": "La porte 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_Bitterness/75370844e9c142efb6120ee67235d1dd5b68a1d34d942daf2981f0ccc836fd73.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": "75a2bd7c910d7ecc95844389e474a10f9fbf4123d0949472b989f35c00d2872d", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fdd6db786279df4f3cadc5561a3ecfbb648517bc16c92525d371c1d6b21a9240", "generation_seconds_batch": 22.829724543960765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11694300174713135, "target_z": -0.2519531177048519, "ce": 5.756534099578857, "genuineness": 4.595211505889893, "identity": 0.6080008149147034, "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_Bitterness/75a2bd7c910d7ecc95844389e474a10f9fbf4123d0949472b989f35c00d2872d.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "75eb5f21c0cb47685410d80f910d66db443a58852aa66fcbf6c66090b5072e95", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "cd79bf3405771835a8621d16ef4d5510a236f0e7943966dda5d815282bc5cdc3", "generation_seconds_batch": 22.25143444503192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13283857703208923, "target_z": -0.2128906171326834, "ce": 6.229123115539551, "genuineness": 4.457139015197754, "identity": 0.5165612101554871, "hypothesis": "La porte 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_Bitterness/75eb5f21c0cb47685410d80f910d66db443a58852aa66fcbf6c66090b5072e95.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "7626dc50d39485be17eb5aa559afd1cf11570ece539f38b43a0d458e912bc230", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "eaa24a0f8f4f36a1821b2dfba5337a91f52846588728f0c83720f33db3bc2b72", "generation_seconds_batch": 23.833496738923714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18529397249221802, "target_z": -0.08398437256828396, "ce": 6.070269584655762, "genuineness": 4.369274139404297, "identity": 0.662181556224823, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7626dc50d39485be17eb5aa559afd1cf11570ece539f38b43a0d458e912bc230.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": "768ebc73995e634e85c12fd22844403566db0aff1fb6870a33dbe26b78be2529", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78d68876cab8a89b426ee5178ec1785281d6a7767f05a82adc213c3de5422e6c", "generation_seconds_batch": 20.789215727942064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13283857703208923, "target_z": -0.2128906171326834, "ce": 5.6254801750183105, "genuineness": 4.570107460021973, "identity": 0.6627793312072754, "hypothesis": "Dos llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/768ebc73995e634e85c12fd22844403566db0aff1fb6870a33dbe26b78be2529.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "76b8516bb3952de098be88238b8bee64fd3bee7dd10cb4346b83dc4198ed04f7", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b609797608974e5948d5c641d3882d3f073746a604579cc8fca57ffea70d13db", "generation_seconds_batch": 23.920489523909055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12568557262420654, "target_z": -0.2304687314045244, "ce": 5.5659098625183105, "genuineness": 4.243753433227539, "identity": 0.4365469813346863, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschneben.", "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_Bitterness/76b8516bb3952de098be88238b8bee64fd3bee7dd10cb4346b83dc4198ed04f7.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "76bd2c9fa4a33b67f43ff0de8318a0f73a4b8d3153b6c1ee82895e000315aa44", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1657adccab036e4af1d2d9d3dd89e9f890c9e0deae1259cbbbdcffa9d9b9699b", "generation_seconds_batch": 23.151342639001086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15906627476215363, "target_z": -0.1484374948504837, "ce": 5.959072113037109, "genuineness": 4.532451152801514, "identity": 0.5833392143249512, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/76bd2c9fa4a33b67f43ff0de8318a0f73a4b8d3153b6c1ee82895e000315aa44.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "76cf64d083c4a93ee765fd46ced4d2468dbf8e6479986cf91195afce47e8f2c1", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b2db39993a72032676f26c544e7e42dcf3a4f575ff6f3ebd361f1a5eff643545", "generation_seconds_batch": 15.904753869050182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029517337679862976, "target_z": -0.4667968708517785, "ce": 6.340320587158203, "genuineness": 4.65797233581543, "identity": 0.14710351824760437, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/76cf64d083c4a93ee765fd46ced4d2468dbf8e6479986cf91195afce47e8f2c1.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": "76d7e3aee4b4ca4e408067bc61e1d799e102a749f2b9429769d1d996c6f37879", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I wrote the number on the envelope.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1c540565a763c63b2d932875d17fb1b14e7308120097bc355ce4872bee5d0396", "generation_seconds_batch": 18.5280193380313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1455550342798233, "target_z": -0.18164062399870515, "ce": 6.24500846862793, "genuineness": 4.582659721374512, "identity": 0.19683738052845, "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_Bitterness/76d7e3aee4b4ca4e408067bc61e1d799e102a749f2b9429769d1d996c6f37879.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "77024831cb3943112841f0452bd282b33f60e07cf03d4177dabc33adcc6c6169", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3fb061c5b009e18557cc7693f17a598a1f7d81b7af06e163262541bb1766e24a", "generation_seconds_batch": 27.326148562016897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06687194108963013, "target_z": -0.37499999084530433, "ce": 6.141753673553467, "genuineness": 4.243753433227539, "identity": 0.3846549391746521, "hypothesis": "The door is still open. Put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/77024831cb3943112841f0452bd282b33f60e07cf03d4177dabc33adcc6c6169.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "74484823ab079b6c2abb9d10cebf63b2b5c1aaa7084a7654a8d983a33375ea36", "generation_seconds_batch": 17.915722636971623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03190167248249054, "target_z": -0.4609374994278315, "ce": 6.149696350097656, "genuineness": 4.507347106933594, "identity": 0.7307102680206299, "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_Bitterness/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "77f8e1235f1fe27bc72ebeb1277a023561f759958a2d1c908d6cbce150ad4b41", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f4291af04a218b99800a6c3436bacbb38dce5cd498bebeeef2ed2be1e07b0aff", "generation_seconds_batch": 16.8462101490004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12171167135238647, "target_z": -0.24023437485695787, "ce": 6.356205940246582, "genuineness": 4.406930446624756, "identity": 0.24268315732479095, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/77f8e1235f1fe27bc72ebeb1277a023561f759958a2d1c908d6cbce150ad4b41.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "86e814cc061832b26f0b58745e3de2fe571514e622d8ff0744849c4104851e49", "generation_seconds_batch": 16.189613151014782, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08833096921443939, "target_z": -0.3222656114109986, "ce": 6.221180438995361, "genuineness": 4.306513786315918, "identity": 0.39253637194633484, "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_Bitterness/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "7958cc737d6ea30372cd83c09f5b13a90a95b4d377bd01e71735ee04eb31ceed", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c28885e250a77827f1cb214d780de8dc3d2ba5143689016ac0ec3fbde6fb2703", "generation_seconds_batch": 23.182705346029252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04382334649562836, "target_z": -0.4316406423080965, "ce": 6.213237762451172, "genuineness": 4.7081804275512695, "identity": 0.627692699432373, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7958cc737d6ea30372cd83c09f5b13a90a95b4d377bd01e71735ee04eb31ceed.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "79d5077e5156a7caa706f3bb2d17e855e69f0feea53c6408b5a1b916215084de", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c2fb38c11f5ae241416d8f78a14a8beaa8fbb213027653c6a2a94043858e2e1b", "generation_seconds_batch": 23.528279343037866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13999158143997192, "target_z": -0.1953125028608424, "ce": 6.046441555023193, "genuineness": 4.796044826507568, "identity": 0.7104611396789551, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/79d5077e5156a7caa706f3bb2d17e855e69f0feea53c6408b5a1b916215084de.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "7a2f201b69bddfd232d0c0ee544f8fcdc4cf87efac55ed5d2892acada676e72b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "35a960b892d690b21a65e7bbe0a750b9bdffc447e658f9b5348f36e120db1ccb", "generation_seconds_batch": 22.484359386959113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9760987758636475, "target_z": 1.8593748661125757, "ce": 5.863759994506836, "genuineness": 4.193545341491699, "identity": 0.5169861316680908, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7a2f201b69bddfd232d0c0ee544f8fcdc4cf87efac55ed5d2892acada676e72b.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "7a93a08c3c122e9867909069f253a5f33101ef83d8f17b511733301772466b9a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "87e00787fae7430b9c0bc83ddfe7a45e4e06e2d8fef137fd08a6817229564913", "generation_seconds_batch": 24.760904751019552, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5246645212173462, "target_z": 0.7500000549281741, "ce": 5.7128496170043945, "genuineness": 4.218649387359619, "identity": 0.45310741662979126, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7a93a08c3c122e9867909069f253a5f33101ef83d8f17b511733301772466b9a.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": "7aed16cec855af1d06ef4bf64817f42a7a51c935ff6d85d25a7f551e38f6b40a", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ff5691620c27791ef547de54dff70e2c79dd24e415fe6496b3ca3be14ba61810", "generation_seconds_batch": 18.41936960304156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17257751524448395, "target_z": -0.1152343657022622, "ce": 5.903473377227783, "genuineness": 4.65797233581543, "identity": 0.39859268069267273, "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_Bitterness/7aed16cec855af1d06ef4bf64817f42a7a51c935ff6d85d25a7f551e38f6b40a.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "7b01b334572acf3c1d964ce3a293f01b97ecaf1843525f9c9094b9babc7e2529", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2aca7554762942774a9a6e4bc9823edc8f900eab042a0a9b574d9339589c851d", "generation_seconds_batch": 20.919797790935263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17734618484973907, "target_z": -0.1035156228543682, "ce": 5.335572719573975, "genuineness": 4.444586753845215, "identity": 0.6793406009674072, "hypothesis": "ist noch offen. Ich habe deinen Mantel auf den Stuhl geleckt. Sag mir, wenn du bereit bist.", "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_Bitterness/7b01b334572acf3c1d964ce3a293f01b97ecaf1843525f9c9094b9babc7e2529.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "7c020e7e649e148bd2ef9f7b15baa4be74ebad297975e90a8f07c0baf3e6d928", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4d8157b1e40030f8f5eac20e1212eecc9317247e04d49cd2cb7a170af253fe13", "generation_seconds_batch": 22.20074590703007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13840201497077942, "target_z": -0.19921877488932888, "ce": 5.935244083404541, "genuineness": 4.65797233581543, "identity": 0.6696451306343079, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7c020e7e649e148bd2ef9f7b15baa4be74ebad297975e90a8f07c0baf3e6d928.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "7cbe6360151ca5e433abeb388cea116c190236fce22b6ec0682d0ce9c21a7c43", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9b09b65aa769f2033cee60f2d1a1f50be224ecbfa2522a0e82d08ddbc883153c", "generation_seconds_batch": 22.716509531019256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18847309052944183, "target_z": -0.07617186513009372, "ce": 5.534139156341553, "genuineness": 4.532451152801514, "identity": 0.625990629196167, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7cbe6360151ca5e433abeb388cea116c190236fce22b6ec0682d0ce9c21a7c43.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "7d1f1b41c328c84b88875eff63e55009367feea98698c1cb6c85c75b532b2b8f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d19ce07903782dfbea3e4e80325e11178bcf5c01c0cc5f4dc1a68a470bb2a66d", "generation_seconds_batch": 23.14082531898748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6041423678398132, "target_z": 0.945312484551451, "ce": 6.046441555023193, "genuineness": 4.369274139404297, "identity": 0.4873664975166321, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7d1f1b41c328c84b88875eff63e55009367feea98698c1cb6c85c75b532b2b8f.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "7d2d31f93646e8193e70db8c28bf4d4d2263d0790173c3391ba30b35b4342df3", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "32181cc4c841582f402386814371a2e2d4492930091a69a75291bb6bc855e4e4", "generation_seconds_batch": 24.806414193008095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17257751524448395, "target_z": -0.1152343657022622, "ce": 5.871703147888184, "genuineness": 4.469690799713135, "identity": 0.17499521374702454, "hypothesis": "La porte 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_Bitterness/7d2d31f93646e8193e70db8c28bf4d4d2263d0790173c3391ba30b35b4342df3.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "7d6c589d008cf16f5b6c3c382a42799518b33a8c8761c3114bd2ea264bf2f16d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2debcd01ba0b9c8ab5c6095e5ed972c7b7e509d4ccea18bcf704065a6ff6c213", "generation_seconds_batch": 22.548143638996407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15906627476215363, "target_z": -0.1484374948504837, "ce": 5.847874641418457, "genuineness": 4.6705241203308105, "identity": 0.7696852684020996, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7d6c589d008cf16f5b6c3c382a42799518b33a8c8761c3114bd2ea264bf2f16d.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "7d73c237cce105ade4f0a1e0edc52f077e3271332af7405bcec99282f20fc833", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "cb58107806ce8127cb1dd33f03cc767e612a6afcf2090821d2d8923a5e7fc0c3", "generation_seconds_batch": 22.567030510981567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1717827320098877, "target_z": -0.11718750171650544, "ce": 5.855817794799805, "genuineness": 4.494794845581055, "identity": 0.44507431983947754, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7d73c237cce105ade4f0a1e0edc52f077e3271332af7405bcec99282f20fc833.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "7dcf3ec3a37aefad55e04b7d50e02e0c67aa2cee9bd5d9bc2c2f08ba20321f61", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "dc1284ea3a39812d29953f7b1b49883edf5027c10811e9a3e45e8853d13ddd36", "generation_seconds_batch": 22.63926356495358, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016006097197532654, "target_z": -0.5, "ce": 6.300607204437256, "genuineness": 4.507347106933594, "identity": 0.32857614755630493, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7dcf3ec3a37aefad55e04b7d50e02e0c67aa2cee9bd5d9bc2c2f08ba20321f61.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "7e4ea7c8dbc50f1271ccae845bc517fe19a30acf764d1c5d328278329998c90b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8e0464ad1449b149f428f6a8025b4625bc25f8bb0929efb903bbaac4821141e2", "generation_seconds_batch": 22.837369419983588, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17019318044185638, "target_z": -0.1210937371262092, "ce": 6.0146708488464355, "genuineness": 4.519899368286133, "identity": 0.6906864643096924, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7e4ea7c8dbc50f1271ccae845bc517fe19a30acf764d1c5d328278329998c90b.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "7e5e2c68b217d17a9c8f8d831d9bd98d74d2ff13f2fe58b07a4af5dce3824bec", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "84d44786bca0a86511b95b24839923065ee8128abdb91a023a76b4158021ffd1", "generation_seconds_batch": 24.416166351991706, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22582769393920898, "target_z": 0.01562501487638048, "ce": 6.149696350097656, "genuineness": 4.425758361816406, "identity": 0.5313160419464111, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7e5e2c68b217d17a9c8f8d831d9bd98d74d2ff13f2fe58b07a4af5dce3824bec.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "7e88ca96605d4f395b350b39cb1597a67c5dd819b5e8d6651e5f402922d4eeff", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78713ba2ec96dfbd16558bd1aa949d77731f749817b579043ea6e7c2b8d6a40f", "generation_seconds_batch": 22.799222811008804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26040056347846985, "target_z": 0.1005859371423947, "ce": 5.982900142669678, "genuineness": 4.419482707977295, "identity": 0.17880460619926453, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7e88ca96605d4f395b350b39cb1597a67c5dd819b5e8d6651e5f402922d4eeff.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "7e9bf3d57d9c77cf7ec53d0ed99d14c9bb41fedb02c3888cd2f8a9713215423e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9ed8199c05229078a8dfcc17433294d9be0731d30d29ec715f928732f3f7699d", "generation_seconds_batch": 24.407182850060053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20516343414783478, "target_z": -0.03515626516246472, "ce": 6.0305562019348145, "genuineness": 4.6203155517578125, "identity": 0.37721937894821167, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7e9bf3d57d9c77cf7ec53d0ed99d14c9bb41fedb02c3888cd2f8a9713215423e.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "7efb2e7c917831043c5958f7a4cdc86f9aa7b083993cf0c1d52ef458521adbcc", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fc0545a6a35d1ba8da0a92d10864a93e48d768913d21598ac71ba9a2055594cb", "generation_seconds_batch": 17.860719718039036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5024106502532959, "target_z": 0.6953123930044942, "ce": 5.685050010681152, "genuineness": 4.262581825256348, "identity": -0.06086569279432297, "hypothesis": "Ik heb het kleine doosje gevonden. Het stomt naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7efb2e7c917831043c5958f7a4cdc86f9aa7b083993cf0c1d52ef458521adbcc.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": "7f2fbae018fca677c5c9872beed1411f6e88ccac9fce745b50971865eaaa222b", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c5db1f9f9eb33b64f0741c73d4b33113b2c3dcce4a31021d08719f5b136d29dc", "generation_seconds_batch": 23.5355758179212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7535607814788818, "target_z": 1.3125000045773478, "ce": 5.593709468841553, "genuineness": 3.860914945602417, "identity": 0.5051378011703491, "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_Bitterness/7f2fbae018fca677c5c9872beed1411f6e88ccac9fce745b50971865eaaa222b.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3d55fbe4932bea5b6b53aca9679844acd583a39e227de6d1fb98aa2897588985", "generation_seconds_batch": 19.66906708793249, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017595648765563965, "target_z": -0.49609376459029625, "ce": 6.372091293334961, "genuineness": 4.532451152801514, "identity": 0.3629785180091858, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "7fe639df8fd1d84dc36cff0083bd0db79bab8229ad8dac1bb1cc2300e2cf2019", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b3bd3c3894ae22f4c34003a31cf02c9f9bdd1b5a291abfff499f2e7168872202", "generation_seconds_batch": 19.36377520102542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05653981864452362, "target_z": -0.40039061255533553, "ce": 5.998785495758057, "genuineness": 4.507347106933594, "identity": 0.6714949607849121, "hypothesis": "La porte 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_Bitterness/7fe639df8fd1d84dc36cff0083bd0db79bab8229ad8dac1bb1cc2300e2cf2019.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "7fe8e7004078866104dadec9312d2dd0d042869bb474595ba94995e234b7db34", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1e9b4b7a1953012c0b1516fb4d7029f360486216cd3068a2d69613a6d8e0b034", "generation_seconds_batch": 20.246629150002263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04143901169300079, "target_z": -0.4375000137320435, "ce": 6.2767791748046875, "genuineness": 4.400654315948486, "identity": 0.653869092464447, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/7fe8e7004078866104dadec9312d2dd0d042869bb474595ba94995e234b7db34.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "80086074926a63cbd8b4572243e8421d0bea4a91abccf494364b8884c47feaa0", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "361f8c95551b26bcc90176c793c1463c38f55e0331860cba8e01690acde8e3ce", "generation_seconds_batch": 21.9847055550199, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09151007235050201, "target_z": -0.3144531405915911, "ce": 5.935244083404541, "genuineness": 4.482243061065674, "identity": 0.9016307592391968, "hypothesis": "La porte 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_Bitterness/80086074926a63cbd8b4572243e8421d0bea4a91abccf494364b8884c47feaa0.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "7b582427ad529c4f57ed78272e643c5cca8f89940c4a99a08bf8e801dd267474", "generation_seconds_batch": 17.536666880943812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03905467689037323, "target_z": -0.44335938515599055, "ce": 6.300607204437256, "genuineness": 4.243753433227539, "identity": 0.6355233788490295, "hypothesis": "Las llaves están en la mesa de la cocina. Mire en el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "80de89abd694bbde7143048e2d7463a6d432ab1506363e6004b8c360b1fd55f8", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "48e524af05fccf851fc9ecdef3c698ee712239dfe6988edef2f6d95da96e5a71", "generation_seconds_batch": 21.236929983948357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08038318157196045, "target_z": -0.34179686169708284, "ce": 6.173524379730225, "genuineness": 4.65797233581543, "identity": 0.6356741786003113, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/80de89abd694bbde7143048e2d7463a6d432ab1506363e6004b8c360b1fd55f8.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": "8198e6b15e37fd94cea5ac8c8bde486c233bc03689d73adadd847fda898442c1", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I wrote the number on the envelope.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a3166b0b296782c2fe98f1135d0ca6bcc70a8a6231008d70cdb9741bd7dc512a", "generation_seconds_batch": 18.5280193380313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12886467576026917, "target_z": -0.2226562605851169, "ce": 6.3641486167907715, "genuineness": 4.457139015197754, "identity": 0.3421056270599365, "hypothesis": "Uh wrote the number on the envelope, read it carefully, and check the last two digits. Call me when you have a moment.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/8198e6b15e37fd94cea5ac8c8bde486c233bc03689d73adadd847fda898442c1.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "823aa7be30f3850bb69b97031bd5afee05c8250b47520a5a89202f347d353a8f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1b2b50e96fe678eaae09c2f53bcab198db1e3afa006ef13c67278f4f58bb30c4", "generation_seconds_batch": 23.548228336963803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.020553722977638245, "target_z": -0.5898437439922309, "ce": 6.213237762451172, "genuineness": 4.425758361816406, "identity": 0.4282451570034027, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/823aa7be30f3850bb69b97031bd5afee05c8250b47520a5a89202f347d353a8f.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "82e3ab214f595cfdb8e201a4b4aa33513dfe5343431981de9d76e7dda634cbe5", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0a106d519cee1986ef9d4f59fc35e587b97da8a96dd26ecc2f41ca4b4189c634", "generation_seconds_batch": 22.63926356495358, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03168061375617981, "target_z": -0.6171874650977227, "ce": 6.459460258483887, "genuineness": 4.607763767242432, "identity": 0.34465786814689636, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/82e3ab214f595cfdb8e201a4b4aa33513dfe5343431981de9d76e7dda634cbe5.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "83a3d59a9014e9e2e7c9d297d16dadcd8c58aab3f6018b8a01edc03d139da58f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e4c15c2ef473bd2c02155769523c83fa05f9d32eae69d0fcd56147ef8f728714", "generation_seconds_batch": 22.7656983199995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10343176126480103, "target_z": -0.28515624685307334, "ce": 5.665193557739258, "genuineness": 4.381826400756836, "identity": 0.6790342330932617, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/83a3d59a9014e9e2e7c9d297d16dadcd8c58aab3f6018b8a01edc03d139da58f.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": "83c3e5a229927cb1bf89280de4f8870d4287009c65115739f14509e9730be6fa", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5b7064245772e705455450be6bb59cdb6e9a4b16d39e55f330ee97c6009d7b02", "generation_seconds_batch": 21.28429691295605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37047743797302246, "target_z": 0.3710937920543833, "ce": 6.308549880981445, "genuineness": 4.532451152801514, "identity": 0.5574558973312378, "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_Bitterness/83c3e5a229927cb1bf89280de4f8870d4287009c65115739f14509e9730be6fa.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "846526ffbeca6045ab169a7cae94a83a6234ac15c174303b00d93e11759e8111", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c1c3a74023915146508dc9d3f8a0f8d7ec5d634d9beb43c6ffb9c3ae6886e36a", "generation_seconds_batch": 23.097981424070895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15827149152755737, "target_z": -0.15039063086472693, "ce": 6.173524379730225, "genuineness": 4.243753433227539, "identity": 0.29178252816200256, "hypothesis": "The door is still open. I put your coat on me when you are ready.", "wer": 0.16666666666666666, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/846526ffbeca6045ab169a7cae94a83a6234ac15c174303b00d93e11759e8111.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "84e8af6388f0a53a64d212d104ffb8a707b0ed9069961a559af832c67cc06dcc", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a34aa8ecb6491b8e2abe116be4292c0045133df65c1ed9bb5d12cf7bb2d3fca3", "generation_seconds_batch": 24.499026159988716, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003289639949798584, "target_z": -0.5312499931339782, "ce": 6.205295085906982, "genuineness": 4.406930446624756, "identity": 0.3260386884212494, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/84e8af6388f0a53a64d212d104ffb8a707b0ed9069961a559af832c67cc06dcc.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "854d24a8ddf2d49d7c10487f17eef4ef4d77e596e9c74b18a468380dd10e51fe", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "490c991209fc5c9e9dd121e7e48d4b3fb49120445be65d4ab1d2853fb6f5a247", "generation_seconds_batch": 23.306813905015588, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21072688698768616, "target_z": -0.021484386300327483, "ce": 6.046441555023193, "genuineness": 4.6203155517578125, "identity": 0.5844419002532959, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/854d24a8ddf2d49d7c10487f17eef4ef4d77e596e9c74b18a468380dd10e51fe.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "88320d88fc6152cee3fffd2435aaf1da3f6b5c807d1f0e0e3a6ac04b46b3b56d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "89efc111837bcb0cba860903767f9a5164da64b7d10b365e90d29d6246a96523", "generation_seconds_batch": 23.33658838190604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2536449432373047, "target_z": 0.08398437256828396, "ce": 5.990842819213867, "genuineness": 4.281409740447998, "identity": 0.6004384756088257, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/88320d88fc6152cee3fffd2435aaf1da3f6b5c807d1f0e0e3a6ac04b46b3b56d.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "891547d9c5f0ac39963949fe272830dfad2c2f2e30f12c10d8ee4faf628bea2d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6d85ab08bb45accfaacb7b6dfbe4d60b5a83bbd42d852749c76bd0c06b3a0a09", "generation_seconds_batch": 25.01043241401203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02077476680278778, "target_z": -0.488281257152106, "ce": 6.38003396987915, "genuineness": 4.582659721374512, "identity": 0.44727572798728943, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/891547d9c5f0ac39963949fe272830dfad2c2f2e30f12c10d8ee4faf628bea2d.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "89dc3cead6a33adac2120a7a8b55b91b9bd82e2b675d4c27f184bd78665ab938", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2caa5d4733b88811ed2851e51665579026bbff8dcf4b4f7c94054827adad4c73", "generation_seconds_batch": 19.13791134406347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1352229118347168, "target_z": -0.2070312457087364, "ce": 6.125868320465088, "genuineness": 4.369274139404297, "identity": 0.7469896078109741, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/89dc3cead6a33adac2120a7a8b55b91b9bd82e2b675d4c27f184bd78665ab938.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "8b0e7716f6020e662291573df9c04e3dc90e1569a93ed7d8377820271c640369", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f156d1b9a0ab4a39a7280ad1e7889892b6b9afc9ed7cbe5643a05061db355cc8", "generation_seconds_batch": 24.625534544000402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16224539279937744, "target_z": -0.14062498741229343, "ce": 5.665193557739258, "genuineness": 4.406930446624756, "identity": 0.5054999589920044, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/8b0e7716f6020e662291573df9c04e3dc90e1569a93ed7d8377820271c640369.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "8b70341d9ec8357f353f269ef42d189a285c49f61bbd9dde2889063d26d2b6f1", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6dceb0ee16a9c99908fc667eae96a0e6639a71551a4fff6e9d890333b82c4232", "generation_seconds_batch": 23.553593727992848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08117794990539551, "target_z": -0.33984376230162233, "ce": 6.006728172302246, "genuineness": 4.545003414154053, "identity": 0.784527063369751, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/8b70341d9ec8357f353f269ef42d189a285c49f61bbd9dde2889063d26d2b6f1.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "8bb100cecf903179b1587cd8a98cf569a0949c9bdd9d35532baa32c46db09a7a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8637ab11bd03f1d1f319480ad65ad24b3411f5dd897f21408169f95692ec0424", "generation_seconds_batch": 24.722081487998366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10025264322757721, "target_z": -0.2929687542912636, "ce": 5.3514580726623535, "genuineness": 4.369274139404297, "identity": 0.5280804634094238, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/8bb100cecf903179b1587cd8a98cf569a0949c9bdd9d35532baa32c46db09a7a.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "8bf2d6e5f0319202f6ee52581acbf4f806240601ca1813d1682531a5aecd1385", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6cbbe90ed85dd320b618143d89adbb2ab62944399832787a3ebbb5536a39a069", "generation_seconds_batch": 22.167185790953226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023159101605415344, "target_z": -0.48242188572815903, "ce": 6.205295085906982, "genuineness": 4.149612903594971, "identity": 0.4075852632522583, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/8bf2d6e5f0319202f6ee52581acbf4f806240601ca1813d1682531a5aecd1385.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "8c2bbc405a7a573334c036fb5d64f222de2ca56310c771f9f86e0fd03b643368", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a973465ac0cc0384edb1f02a33508e8a3705c5aca5e47d186fcc6d9ee2a5c23a", "generation_seconds_batch": 23.171261124080047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5755303502082825, "target_z": 0.875000027464087, "ce": 4.856033802032471, "genuineness": 4.036643981933594, "identity": 0.519912600517273, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/8c2bbc405a7a573334c036fb5d64f222de2ca56310c771f9f86e0fd03b643368.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": "8cd3b612182cddcf9d0122b5d23d83dfe4d9507631b907ac14b52e7d9f808a12", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f17805234986d02c7051ba5098d2e3f8a6e16fd1d5a43181c85929425dc641ab", "generation_seconds_batch": 16.256222896976396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20277909934520721, "target_z": -0.04101563658641172, "ce": 6.0146708488464355, "genuineness": 4.281409740447998, "identity": 0.6246049404144287, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de aan de andere kant.", "wer": 0.14285714285714285, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/8cd3b612182cddcf9d0122b5d23d83dfe4d9507631b907ac14b52e7d9f808a12.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "8d0f862a1cbf6aa58327eed83d59e09e1a58273582cf802235cc89cbed7b8eab", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a29e4d339533f4a55c10758fd415fbd4f527d45f3f39f638c3786b6a8a729700", "generation_seconds_batch": 17.290502845076844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15986105799674988, "target_z": -0.14648435883624045, "ce": 5.772419452667236, "genuineness": 4.231201171875, "identity": 0.6311749219894409, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/8d0f862a1cbf6aa58327eed83d59e09e1a58273582cf802235cc89cbed7b8eab.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "8d602e0295d1fdc04547955361edd06c0570a0d46d174a361715d9367f14145e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e9a4ac5e0ac836e48a303b6c5acd0227b3ba0d03b7aa5f0f583f6deb1917689b", "generation_seconds_batch": 21.41195596207399, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02214328944683075, "target_z": -0.5937500160207174, "ce": 6.324435234069824, "genuineness": 4.425758361816406, "identity": 0.3896620273590088, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/8d602e0295d1fdc04547955361edd06c0570a0d46d174a361715d9367f14145e.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "8d956d757b6ce04fdb0941bb7691e864e6b04e59f75a5a0788482ab83f118ce4", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "042adcc8e049c705d9ae668209af2db4e9d06c8d21e16a6d73f946d7aad2558b", "generation_seconds_batch": 23.785910113016143, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11137954890727997, "target_z": -0.2656249965669891, "ce": 5.059564590454102, "genuineness": 4.143336772918701, "identity": 0.5709203481674194, "hypothesis": "", "wer": 1.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/8d956d757b6ce04fdb0941bb7691e864e6b04e59f75a5a0788482ab83f118ce4.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "8da9b70d9b5ba973ad5178726f9c1761d03748e298e6497feb490d6297086295", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "eeb6d7ba09041cb075360d82062ca0ff7c4b5b3b669ce361f0d8eb04b1f118b0", "generation_seconds_batch": 16.07311039196793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1892678588628769, "target_z": -0.07421876573463321, "ce": 6.086154937744141, "genuineness": 4.369274139404297, "identity": 0.41156262159347534, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/8da9b70d9b5ba973ad5178726f9c1761d03748e298e6497feb490d6297086295.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "8ded0bc47c200f4963f2b1f0e5dba6c58c43665fd559916dd10e2ea53971d38d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1fcf947a01f757942b7e34162b6fe22bff73484e4da76b44319251af7c6298f8", "generation_seconds_batch": 22.959730934002437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0430285781621933, "target_z": -0.433593741703557, "ce": 6.141753673553467, "genuineness": 4.607763767242432, "identity": 0.3388723134994507, "hypothesis": "My door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/8ded0bc47c200f4963f2b1f0e5dba6c58c43665fd559916dd10e2ea53971d38d.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "8e66ffe39daa67a20b3683737cb8386c61d8220e741ca8e031f69dd477c1fc8e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b6d47bba1d039461bfd61cd2a07366ad2732606201c15f063868faa4381154bf", "generation_seconds_batch": 22.79008430801332, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06846149265766144, "target_z": -0.3710937554356006, "ce": 6.141753673553467, "genuineness": 4.7332844734191895, "identity": 0.6346702575683594, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/8e66ffe39daa67a20b3683737cb8386c61d8220e741ca8e031f69dd477c1fc8e.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "8e7de96f7a00993e51d5d57dbb94e26482c7d4eb519b44025471a9f83a4a2f9c", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "cc6ce172d86421983a40ba3c47c41bc98ce716e05c4a9d67b3e278e77aa625ef", "generation_seconds_batch": 16.081408399972133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20357388257980347, "target_z": -0.03906250057216848, "ce": 5.8875885009765625, "genuineness": 4.268857479095459, "identity": 0.6838726997375488, "hypothesis": "De deur staat nog open. Ik heb je juist 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_Bitterness/8e7de96f7a00993e51d5d57dbb94e26482c7d4eb519b44025471a9f83a4a2f9c.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "8f12d7fee271f7bb8377deb82d40a237a8cf1b7e1767edc371b1bd29cd487fad", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0e847d8cbf1f2ad467c75b65eac5243869cad29fce7cf47918c65a2b20feda9b", "generation_seconds_batch": 16.798076200997457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12886467576026917, "target_z": -0.2226562605851169, "ce": 6.141753673553467, "genuineness": 4.507347106933594, "identity": 0.5729556679725647, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/8f12d7fee271f7bb8377deb82d40a237a8cf1b7e1767edc371b1bd29cd487fad.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "8f3bfcc5832fcb03415e04d99fb8eb333b295433392e0579ea2117b9899729e1", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c1a8346b6ecbb60f081a82dadf9a7d926fe10eb37cc07055b0b13f8b2146a74c", "generation_seconds_batch": 23.444103364017792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05653981864452362, "target_z": -0.40039061255533553, "ce": 5.974957466125488, "genuineness": 4.582659721374512, "identity": 0.6591817140579224, "hypothesis": "La porte 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_Bitterness/8f3bfcc5832fcb03415e04d99fb8eb333b295433392e0579ea2117b9899729e1.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "8f3ea096e6b07219eaca4e2438bcd9b87aaf5e0512b4db0581c507d378749414", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a2a2a2b2614ea16e272299b67c83f511fccd6eb34621bb014bfc7c72d8963f52", "generation_seconds_batch": 22.847386668086983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15827149152755737, "target_z": -0.15039063086472693, "ce": 5.700935363769531, "genuineness": 4.595211505889893, "identity": 0.7039540410041809, "hypothesis": "La porte 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_Bitterness/8f3ea096e6b07219eaca4e2438bcd9b87aaf5e0512b4db0581c507d378749414.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": "8f8f9492c66161421a5f6ac0591554d9465a1524dd9dc7ec8aff6e5d545d2e98", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The keys are on the kitchen table.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0dfe33dd198e7f87b5a9496660241f94bdbe3e86f1021b5984b4a4bcb2db7578", "generation_seconds_batch": 25.243173866998404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07879361510276794, "target_z": -0.3457031337255693, "ce": 6.23706579208374, "genuineness": 4.356721878051758, "identity": 0.2713128328323364, "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_Bitterness/8f8f9492c66161421a5f6ac0591554d9465a1524dd9dc7ec8aff6e5d545d2e98.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "8fb428e3cef00537747b212edeb07ba47827c3045639b02fe9a6989e2ee09dfc", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ada304320df3e8bab140053ba7b67a87a7135b3744adcbb59ffdad3a49ccf4cd", "generation_seconds_batch": 24.328037773026153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08753618597984314, "target_z": -0.3242187474252418, "ce": 5.895530700683594, "genuineness": 4.796044826507568, "identity": 0.6415462493896484, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/8fb428e3cef00537747b212edeb07ba47827c3045639b02fe9a6989e2ee09dfc.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "90149b1cdf833bb4decb2e05f238a9d4bf7f2dbb277957a7875ddaa140231937", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "cdd7fc16c1148e1dfa70ad6f0328b136e5f68fd1f03d15e7d8575f684ea1e03d", "generation_seconds_batch": 16.62556344200857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7058740854263306, "target_z": 1.1953125760984078, "ce": 5.935244083404541, "genuineness": 4.2751336097717285, "identity": 0.6213691234588623, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/90149b1cdf833bb4decb2e05f238a9d4bf7f2dbb277957a7875ddaa140231937.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "9067bf85eda649596402066ec2e4fef6ff74dce0a3401d867b5811934bb21da9", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "82a6961530eec356023d24be4c93c8d7f9af5c562f07cb91bbebaab299b7ead7", "generation_seconds_batch": 21.294508069986477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.062103271484375, "target_z": -0.3867187336931983, "ce": 5.967014789581299, "genuineness": 4.582659721374512, "identity": 0.8040281534194946, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/9067bf85eda649596402066ec2e4fef6ff74dce0a3401d867b5811934bb21da9.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "908d5f2596fb57b4cb8d549bcfc2823fca83946bccaa5efd306ac0f6829efed6", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1c9bb53bd4024e63266ce8476f70670adf65e88574d3ddd66146b67159cbefe8", "generation_seconds_batch": 23.097981424070895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10263697803020477, "target_z": -0.2871093828673166, "ce": 6.109982967376709, "genuineness": 4.143336772918701, "identity": 0.033150143921375275, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/908d5f2596fb57b4cb8d549bcfc2823fca83946bccaa5efd306ac0f6829efed6.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "90babd0588713e8c512261ae2a36bd7d6719688dc7a8ec5d742b36cfc27696b6", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6b9e751e9d80bda83278b6926b89226e166018a100fb4bacd9cc19cf2198eea3", "generation_seconds_batch": 26.332177647971548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6709038019180298, "target_z": 1.109375030897098, "ce": 5.422942161560059, "genuineness": 4.369274139404297, "identity": 0.2002672553062439, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/90babd0588713e8c512261ae2a36bd7d6719688dc7a8ec5d742b36cfc27696b6.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "90cdc6556ddead680810b07de27201f3f4430d87055673b05f89bad96ef73c45", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "bf6afcb3859cd9953279d99da5248982cf14ba1243e0aefe17fb0fca4da99750", "generation_seconds_batch": 23.311395670985803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0795883983373642, "target_z": -0.3437499977113261, "ce": 5.9431867599487305, "genuineness": 4.093128204345703, "identity": 0.6269698739051819, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/90cdc6556ddead680810b07de27201f3f4430d87055673b05f89bad96ef73c45.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "91143b21b7b4eb6a0085ae45420c6251a5e4ef41e4cfef38e6b0606e56af7e6c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3281cf916513aa5aaf0c1b19dfce62b844c991b7cba8d19bd935e4ef2e039837", "generation_seconds_batch": 23.306813905015588, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18529397249221802, "target_z": -0.08398437256828396, "ce": 5.71682071685791, "genuineness": 4.7081804275512695, "identity": 0.5369933843612671, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/91143b21b7b4eb6a0085ae45420c6251a5e4ef41e4cfef38e6b0606e56af7e6c.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "920a055ea6e32c6e0649e33b4f0ab13f930fdf924b9d72c05f7e3fb1ecf5053c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4f5742dcd7a2dd692c9c17d0a141da7d3e3015b51b96c7fdc774b335ef0027c6", "generation_seconds_batch": 22.516891865991056, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07720406353473663, "target_z": -0.3496093691352731, "ce": 6.268836498260498, "genuineness": 4.3881025314331055, "identity": 0.1631733775138855, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/920a055ea6e32c6e0649e33b4f0ab13f930fdf924b9d72c05f7e3fb1ecf5053c.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "92a1e0157540b69beb31d47cd171d7b599e44c84dacb90639a292854fb7c5abb", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ed55f43b47529a114341663af26a6670662c77cfe49f39cbc1f51c41da68f7f1", "generation_seconds_batch": 17.5668351839995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07323016226291656, "target_z": -0.35937501258770654, "ce": 5.8875885009765625, "genuineness": 4.281409740447998, "identity": 0.5786912441253662, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/92a1e0157540b69beb31d47cd171d7b599e44c84dacb90639a292854fb7c5abb.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": "92a8cab6fe3556e983cce0029e1c75b51ae9e031c6a5e45ae67078cf43de6054", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The road turns left behind the bridge.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5d00555b138e66e35a3358ab51351e30c9310d7abb76fe832fe665e416a67f92", "generation_seconds_batch": 17.491377745987847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08435706794261932, "target_z": -0.3320312548634321, "ce": 6.316492557525635, "genuineness": 4.162164688110352, "identity": 0.3416866064071655, "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_Bitterness/92a8cab6fe3556e983cce0029e1c75b51ae9e031c6a5e45ae67078cf43de6054.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "92f08cfb69067f0350db22c479d6d18694e84418e1c82b8515b3abd245ee9007", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ff06369c3a3e78e6ef37a2508c6c409b30dbb91c3018a5f47c109806fa107dd6", "generation_seconds_batch": 23.68796982697677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09786830842494965, "target_z": -0.2988281257152106, "ce": 5.748591423034668, "genuineness": 4.632867813110352, "identity": 0.617124080657959, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/92f08cfb69067f0350db22c479d6d18694e84418e1c82b8515b3abd245ee9007.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "93d26244375c8d3569a186166e207f06e85333444d87ac26a626ffa4e0b0bcc1", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f986eeb0be0b332a98ecc65783e3f502f35a6a8e5bfaa0e0fc4348fd2db3d723", "generation_seconds_batch": 15.50353637104854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.050755321979522705, "target_z": -0.6640625097268642, "ce": 6.3641486167907715, "genuineness": 4.20609712600708, "identity": 0.3704821467399597, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/93d26244375c8d3569a186166e207f06e85333444d87ac26a626ffa4e0b0bcc1.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "94274dda9c22ff3a21a079a7e57eb141b48cf9359f9793d3489abf1f0e3709e8", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4b241a78786048ebf79424a18a0b2a4b4855457816c4e2ab681c57e38b438ee8", "generation_seconds_batch": 23.220287385978736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13840201497077942, "target_z": -0.19921877488932888, "ce": 5.518253803253174, "genuineness": 4.268857479095459, "identity": 0.23349353671073914, "hypothesis": "La porte 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_Bitterness/94274dda9c22ff3a21a079a7e57eb141b48cf9359f9793d3489abf1f0e3709e8.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "94920fa78bb574b6571c2c85b9bca26fc93f089f78498a9a1da3726c92903b0c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ebde2b15dae2072306c7714eece0fb8c921f0e81b7992145bd3f0f3a3faaab86", "generation_seconds_batch": 23.10640240693465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02633821964263916, "target_z": -0.47460937828996874, "ce": 6.316492557525635, "genuineness": 4.545003414154053, "identity": 0.223965123295784, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/94920fa78bb574b6571c2c85b9bca26fc93f089f78498a9a1da3726c92903b0c.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "94bf01da37239722e82fc14b38698e73220ee4199f57fd04e68a92479c8e1aa8", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b1b86a1906e1adb8f2e29f27777c22d80ca4807b80faf48a212a65d045e7b3c0", "generation_seconds_batch": 26.022872249945067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17257751524448395, "target_z": -0.1152343657022622, "ce": 5.77639102935791, "genuineness": 4.6203155517578125, "identity": 0.25970658659935, "hypothesis": "La porte 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_Bitterness/94bf01da37239722e82fc14b38698e73220ee4199f57fd04e68a92479c8e1aa8.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "957e6734d0135958571f0777a17a61b827cec25478763cb64e19a0c605d964c9", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "309f2b6c1065ca66f81326edd942629f48e86791eddb0cdb2b06bd09f1d6d5d4", "generation_seconds_batch": 23.47615922393743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07879361510276794, "target_z": -0.3457031337255693, "ce": 5.8875885009765625, "genuineness": 4.582659721374512, "identity": 0.6623408198356628, "hypothesis": "J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.2777777777777778, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/957e6734d0135958571f0777a17a61b827cec25478763cb64e19a0c605d964c9.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "95831045e6ed20ab7f16f63742808801ae99b399433de8245b32620abf96c9c9", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b27811fa904aac713111bf3cd78b1e8dbd7af9c3b82df8f8df9244c259435156", "generation_seconds_batch": 25.315636298037134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1336333453655243, "target_z": -0.21093751773722288, "ce": 5.319687366485596, "genuineness": 4.262581825256348, "identity": 0.5286718606948853, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/95831045e6ed20ab7f16f63742808801ae99b399433de8245b32620abf96c9c9.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "95ed7f0ba883f7149daafcb57ed751ba1c072f5faf38dca773169183551e33dc", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "32624dae881bdcd3fe94ca875849a209317eed80f347927be047107ae218ad5f", "generation_seconds_batch": 23.241756162955426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09786830842494965, "target_z": -0.2988281257152106, "ce": 5.5738525390625, "genuineness": 4.570107460021973, "identity": 0.7704614996910095, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/95ed7f0ba883f7149daafcb57ed751ba1c072f5faf38dca773169183551e33dc.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "96815ecb1173f14572508d9b4463f63fceab18c2f2d1254310613b00c309e147", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8ec338ac2917497f1cfc8e50e29da1b5ff140d774a2fd6c57d27443204edbce4", "generation_seconds_batch": 24.728989872033708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07640928030014038, "target_z": -0.3515625051495163, "ce": 6.141753673553467, "genuineness": 4.507347106933594, "identity": 0.8021124601364136, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/96815ecb1173f14572508d9b4463f63fceab18c2f2d1254310613b00c309e147.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "9713f5eb71bca313f8c6b0bb5bf0875eba397f00b91e17ca11329f806a5f8a94", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e3670af57350019fe2f6c801451ed6c0826192520de912133335e269f7569505", "generation_seconds_batch": 17.040048383991234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0430285781621933, "target_z": -0.433593741703557, "ce": 6.046441555023193, "genuineness": 4.632867813110352, "identity": 0.8262443542480469, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/9713f5eb71bca313f8c6b0bb5bf0875eba397f00b91e17ca11329f806a5f8a94.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "97750a032e305c66c9b1a4a87ed5eb0acde16bfd95373921d3a1696d15fb4b17", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "118c9c44dc237979424fe0d1b14a9a440736efaaa0aafd9a6a3f0be9209ac066", "generation_seconds_batch": 24.524506040033884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13840201497077942, "target_z": -0.19921877488932888, "ce": 6.125868320465088, "genuineness": 4.65797233581543, "identity": 0.6308938264846802, "hypothesis": "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_Bitterness/97750a032e305c66c9b1a4a87ed5eb0acde16bfd95373921d3a1696d15fb4b17.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "97ba7ab46a13402ad8c7443036e5a55ecf1d3f8d1b4703aabcbde17aaf26fca6", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "71e50872e936e3c4b278b89ff909d8a68402fc9aa2ab26cccff2c0b29bdffe48", "generation_seconds_batch": 23.849276897963136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39829468727111816, "target_z": 0.43945314974628674, "ce": 6.070269584655762, "genuineness": 4.545003414154053, "identity": 0.5403385758399963, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/97ba7ab46a13402ad8c7443036e5a55ecf1d3f8d1b4703aabcbde17aaf26fca6.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "97bb88ad652e1cba64d2805537046b4d55da7b86e3967fd6617fe72303c61046", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d89039c65d40607304638783a6a9c38c873ccee31d728a9315247f603af39ebc", "generation_seconds_batch": 17.5668351839995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06289803981781006, "target_z": -0.3847656342977378, "ce": 5.808161735534668, "genuineness": 4.20609712600708, "identity": 0.471589595079422, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/97bb88ad652e1cba64d2805537046b4d55da7b86e3967fd6617fe72303c61046.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "97c7738a9ae9894e17a541c853b644681a5f428f2ff932985617c6ed6eddbd13", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e6ab119c385611d3eae06a23a9a4e93d3b32102540950d8ce883c4799f87e2d9", "generation_seconds_batch": 21.3093351299176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06607715785503387, "target_z": -0.37695312685954757, "ce": 6.324435234069824, "genuineness": 4.65797233581543, "identity": 0.2575939893722534, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/97c7738a9ae9894e17a541c853b644681a5f428f2ff932985617c6ed6eddbd13.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "97cab11d558d25ffba7fe2395e3c79397fb06bdec47b71abdb6df66e3ea5de3c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5009bf7a9c73a3c42508e8668899a1bc9f50493bebb72ef6a96764a08066a09f", "generation_seconds_batch": 16.114960588980466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.036670342087745667, "target_z": -0.44921875657993754, "ce": 6.133810997009277, "genuineness": 4.871357440948486, "identity": 0.7098860144615173, "hypothesis": "J'ai trouvé la petite boîte. Elle était fourrée de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/97cab11d558d25ffba7fe2395e3c79397fb06bdec47b71abdb6df66e3ea5de3c.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "97df741d1fb2f69425dc2f9f1bb000f783ef199ae5a7428ea266ba89451b5b2c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8259f619763df4107f1a8a7ac36ed4ca80352a44d86c1de4b333dfbab074bb98", "generation_seconds_batch": 23.148368171066977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06289803981781006, "target_z": -0.3847656342977378, "ce": 6.109982967376709, "genuineness": 4.143336772918701, "identity": 0.17529228329658508, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/97df741d1fb2f69425dc2f9f1bb000f783ef199ae5a7428ea266ba89451b5b2c.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "97ff55afd8ab345732f9a5818fde245e5b72db8e75b7a46e7d7cf811da99a6f1", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "001ce0900ffa7512a655f95eae8e0e6fd53059d826fc56ecba6a3e09168338c5", "generation_seconds_batch": 23.185873958980665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15986105799674988, "target_z": -0.14648435883624045, "ce": 5.685050010681152, "genuineness": 4.256305694580078, "identity": 0.09982754290103912, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/97ff55afd8ab345732f9a5818fde245e5b72db8e75b7a46e7d7cf811da99a6f1.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "981fc96d455946c715955e02c56f6ddb95ff15951aec879ed948c316bd396058", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7bc09a1334cce8c67869e70985a785c4f8dd0d5a11d51e73646c11140071942d", "generation_seconds_batch": 26.022872249945067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17655140161514282, "target_z": -0.10546875886861144, "ce": 5.585766792297363, "genuineness": 4.394378662109375, "identity": 0.24289269745349884, "hypothesis": "La porte 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_Bitterness/981fc96d455946c715955e02c56f6ddb95ff15951aec879ed948c316bd396058.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "989da1ffced21c691e6afc68f6e39fbfc4ca687610563ef19568e629cfafeac7", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c52bb708ee01c8543d6ec5085c21621946d95e2d6c885701187411533b1e3234", "generation_seconds_batch": 16.50593022198882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14714458584785461, "target_z": -0.1777343885890014, "ce": 6.046441555023193, "genuineness": 4.419482707977295, "identity": 0.29962804913520813, "hypothesis": "The 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_Bitterness/989da1ffced21c691e6afc68f6e39fbfc4ca687610563ef19568e629cfafeac7.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "98b471f1cd845c81b8a93dad97e74cfc03fc1f750ed8f8c8626ac70fbee1bf53", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "11c1f4befb50ebf5165b6c725cf371d0a152d180888e5511c67ecba996813f93", "generation_seconds_batch": 21.545055855996907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11535344272851944, "target_z": -0.255859371423947, "ce": 5.804190158843994, "genuineness": 4.8588056564331055, "identity": 0.6326824426651001, "hypothesis": "La porte 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_Bitterness/98b471f1cd845c81b8a93dad97e74cfc03fc1f750ed8f8c8626ac70fbee1bf53.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "98f60252d9949d14fa87cfb85c56b2593b1c87062dd21673e394d77a22b8d492", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e7ef17d28a844ca9efd74bae1780c4b5b2634aa810a44e2160532a3d8402bfa6", "generation_seconds_batch": 16.081408399972133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13760724663734436, "target_z": -0.2011718742847894, "ce": 6.078212261199951, "genuineness": 4.344170093536377, "identity": 0.6803253889083862, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/98f60252d9949d14fa87cfb85c56b2593b1c87062dd21673e394d77a22b8d492.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "98f71d262f5d79c80b20636083ff5e693d86774d0d25e696d0020f05e4da2dfa", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5d6949ba0c6bfe4e44219766ac68dda0190ad1f21fd22ba28041508183538049", "generation_seconds_batch": 23.709817023016512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17655140161514282, "target_z": -0.10546875886861144, "ce": 6.252951145172119, "genuineness": 4.262581825256348, "identity": 0.4991483688354492, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/98f71d262f5d79c80b20636083ff5e693d86774d0d25e696d0020f05e4da2dfa.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "d0517c4a8718ff218e1e89b7dd9a18c01d815ccb1db6437a0f170639066cadd3", "generation_seconds_batch": 16.97746044700034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.070845827460289, "target_z": -0.36523438401165353, "ce": 6.41180419921875, "genuineness": 4.7332844734191895, "identity": 0.405289888381958, "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_Bitterness/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "9a273e84f4f8ea8f3cabe48df0e4c4ee8b9b705c8f01f325b1dce0544d00abf4", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ba50bbe4447db39199fa05403a01af283f280b8fb427705e3ad114f2686d8b1d", "generation_seconds_batch": 17.31518670299556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11217432469129562, "target_z": -0.2636718788621372, "ce": 6.1894097328186035, "genuineness": 4.432034492492676, "identity": 0.6642502546310425, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/9a273e84f4f8ea8f3cabe48df0e4c4ee8b9b705c8f01f325b1dce0544d00abf4.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "9ae5737186c696c012d92f6537cbf78bde043cc83e830337d44f16e294ed829b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a4b50356b577225e1a8122eb31c75ab199da9151105cc8418b78dcb9c0f18887", "generation_seconds_batch": 23.69153708999511, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14078636467456818, "target_z": -0.19335936684659916, "ce": 5.696964263916016, "genuineness": 4.595211505889893, "identity": 0.6031918525695801, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/9ae5737186c696c012d92f6537cbf78bde043cc83e830337d44f16e294ed829b.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "9b0c29bc492a5d3311b34b74ed34048370393c5960be286791edd0eb56c724bd", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7aeb2a7042bdaefd35f828eb39ea8875c6d44274ed1159fdbc7eefe53477bb4b", "generation_seconds_batch": 28.29528961190954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13999158143997192, "target_z": -0.1953125028608424, "ce": 6.078212261199951, "genuineness": 4.432034492492676, "identity": 0.4253304600715637, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen daar samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/9b0c29bc492a5d3311b34b74ed34048370393c5960be286791edd0eb56c724bd.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "9b56c398ade9f5dbed183d9cad32b4b5a719c2de7b43cce2a502cfe565a3adf5", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bd73952871a6969dc792433fe1f9f34ac88ace99a353b3c34f56222e407f8d08", "generation_seconds_batch": 22.995358198997565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031106889247894287, "target_z": -0.46289063544207476, "ce": 6.252951145172119, "genuineness": 4.796044826507568, "identity": 0.7392572164535522, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/9b56c398ade9f5dbed183d9cad32b4b5a719c2de7b43cce2a502cfe565a3adf5.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "9ba518235f988b8f4f81d9b3f96713faf2dd7af98928562f3fd8723faa5a8b4e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7f9f50e07dc5dd4e1f75c6bd2a8e9a319f606cca16a4fa78dd576949f6942a0c", "generation_seconds_batch": 20.210499681998044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16621927917003632, "target_z": -0.1308593805786427, "ce": 6.038498878479004, "genuineness": 4.833701133728027, "identity": 0.7431821823120117, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/9ba518235f988b8f4f81d9b3f96713faf2dd7af98928562f3fd8723faa5a8b4e.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "63c9d10f8e25547c103030b288f6372e15a13cf21a82dbcce23f25e224eb4d9d", "generation_seconds_batch": 17.4171530790627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09786830842494965, "target_z": -0.2988281257152106, "ce": 6.1894097328186035, "genuineness": 4.15588903427124, "identity": 0.7265849709510803, "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_Bitterness/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "9c8f1c30a1a94f9c198ab89a99efb88b3ddc7aba485952086e651fc534837188", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "83b168d92e21477bbb578e21fc314dbc3c064fa91c81a486e7105cfe1edbecdc", "generation_seconds_batch": 20.042053957935423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22662246227264404, "target_z": 0.017578114271841, "ce": 5.903473377227783, "genuineness": 4.68307638168335, "identity": 0.6008418798446655, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/9c8f1c30a1a94f9c198ab89a99efb88b3ddc7aba485952086e651fc534837188.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "8d75b8a355242d7b5e11b69a23c082acc7c520947baa49e2a61f753c5af32c6e", "generation_seconds_batch": 16.50387060898356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12727512419223785, "target_z": -0.22656249599482065, "ce": 6.109982967376709, "genuineness": 4.356721878051758, "identity": 0.5887860059738159, "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_Bitterness/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.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": "9d63fa7a33328d394dafc725a412d87645b2127a25b70b7b5bdb35c579098c58", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cbfd82ad05e3951a5f80be1eeb630fe927d413ed1877002f79f94a94a80f6b39", "generation_seconds_batch": 17.886618123971857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17734618484973907, "target_z": -0.1035156228543682, "ce": 5.935244083404541, "genuineness": 4.65797233581543, "identity": 0.0011091157793998718, "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_Bitterness/9d63fa7a33328d394dafc725a412d87645b2127a25b70b7b5bdb35c579098c58.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "9d7b678512862c442b4edd01adb8b8776a85a3d98f151c6115228b798fd92231", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f4e78e4d92f22db876275cb6d8c348361efd70de8a29d690daa30e0210563550", "generation_seconds_batch": 22.43190692400094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.058924153447151184, "target_z": -0.39453124113138854, "ce": 6.221180438995361, "genuineness": 4.243753433227539, "identity": 0.35776203870773315, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/9d7b678512862c442b4edd01adb8b8776a85a3d98f151c6115228b798fd92231.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": "9da48e4c861bca3625cd9eef6f66a78a3439267b56c776974d499ff8eebdb62d", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c3fb2dfd0f8a14797872dbd1f1f871b60b617018a12436d65e930327a4e6569", "generation_seconds_batch": 23.105930309044197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15827149152755737, "target_z": -0.15039063086472693, "ce": 5.788304805755615, "genuineness": 4.469690799713135, "identity": 0.33640381693840027, "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_Bitterness/9da48e4c861bca3625cd9eef6f66a78a3439267b56c776974d499ff8eebdb62d.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": "9e1815625e67c9f3fa184ca92e7ccd5614638086d3decf9bc9259c3a5fa561ea", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I wrote the number on the envelope.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b3c733bb7c52f6188027616cfa55e2cdebda45e885ce1fbfa991e05e440af666", "generation_seconds_batch": 23.50218565389514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10263697803020477, "target_z": -0.2871093828673166, "ce": 6.2767791748046875, "genuineness": 4.256305694580078, "identity": 0.3507072627544403, "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_Bitterness/9e1815625e67c9f3fa184ca92e7ccd5614638086d3decf9bc9259c3a5fa561ea.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": "9ecc865fa055f23ab64bc643815afb92a386544ec2205b69a3c100bf0fbdc44a", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0d28db91857db34265985d3cc3676e7273e6df24fb4b7b3e6cef3ef4d23aa1ff", "generation_seconds_batch": 24.02683769899886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10104742646217346, "target_z": -0.2910156182770204, "ce": 6.09409761428833, "genuineness": 4.381826400756836, "identity": 0.6203714609146118, "hypothesis": "Ik schreef het nummer op de envelop, lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/9ecc865fa055f23ab64bc643815afb92a386544ec2205b69a3c100bf0fbdc44a.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "9edbc391e74974106d921ea6ca880bbc65fde06a14bf0ff6384a00abccd143a0", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bff1a99a3ec2b790c9146fcb9a91a2034a5b8d8243cee4ac222813b4428014c4", "generation_seconds_batch": 23.90710644493811, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09151007235050201, "target_z": -0.3144531405915911, "ce": 5.974957466125488, "genuineness": 4.331617832183838, "identity": 0.6568073034286499, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/9edbc391e74974106d921ea6ca880bbc65fde06a14bf0ff6384a00abccd143a0.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "9f15214394c107a0de751c3b027df6490f22ebf724c67f45780df1750d5572d8", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c7c37a246f055faa9a2f31465ce1a440e90fac1adc0c45de4adbe7d3b7820ec5", "generation_seconds_batch": 23.533210065914318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2834491431713104, "target_z": 0.15722655198640417, "ce": 6.022613525390625, "genuineness": 4.519899368286133, "identity": 0.42535263299942017, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/9f15214394c107a0de751c3b027df6490f22ebf724c67f45780df1750d5572d8.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "9f8fef044ecadd5ce7aeb899e660e2aa5ddcab39c87048df81f0a09076922b5c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b172e6eb8f524f8fefcfea59f02861a78a701f166d027229583cb45db4f400a2", "generation_seconds_batch": 23.898442486068234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05733458697795868, "target_z": -0.398437513159875, "ce": 6.181467056274414, "genuineness": 3.9550557136535645, "identity": 0.36837390065193176, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/9f8fef044ecadd5ce7aeb899e660e2aa5ddcab39c87048df81f0a09076922b5c.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "9ff93f0ab0a109c898fc48f892a952ab4f3948ce2022d5d8de33c0e2d5ba50f2", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0d85a9bc8218502c06fad9144d3ae80167ed07090e5c5ee41f49f2ac7d0aff7e", "generation_seconds_batch": 23.23725445510354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12330123037099838, "target_z": -0.23632812113786275, "ce": 6.086154937744141, "genuineness": 4.645420074462891, "identity": 0.7407892346382141, "hypothesis": "La porte 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_Bitterness/9ff93f0ab0a109c898fc48f892a952ab4f3948ce2022d5d8de33c0e2d5ba50f2.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "a0118373913416661cf37a917b04f82c9d11e9cca38072c7f1f64990041760b2", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "96c35ddd20adb29c67532cd19f189386c2daaa874d3db0670cece6d2fb336809", "generation_seconds_batch": 16.673365670023486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09548397362232208, "target_z": -0.3046874971391576, "ce": 5.95112943649292, "genuineness": 4.381826400756836, "identity": 0.4540866017341614, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/a0118373913416661cf37a917b04f82c9d11e9cca38072c7f1f64990041760b2.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "a0293957bb4d1999c5d7bc2832995ea5ad7d059a9ccbcff52dfeb70f2b3044cd", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3720fb00911d9c0814cb4aab4237c81884b93e7b34794fc7e07c98f44c24a38a", "generation_seconds_batch": 23.151342639001086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1423759162425995, "target_z": -0.1894531314368954, "ce": 6.070269584655762, "genuineness": 4.457139015197754, "identity": 0.6959677934646606, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/a0293957bb4d1999c5d7bc2832995ea5ad7d059a9ccbcff52dfeb70f2b3044cd.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "a0a3dbc6f897e92794782881b9562d2b6af2d403e56e394166136751db8494a8", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ead9019614947bfc62cb20e7ca43e9c0f2984c578a65311531755ca9cc68bf2f", "generation_seconds_batch": 22.70804410101846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13442812860012054, "target_z": -0.20898438172297965, "ce": 5.919358730316162, "genuineness": 4.68307638168335, "identity": 0.5863279104232788, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/a0a3dbc6f897e92794782881b9562d2b6af2d403e56e394166136751db8494a8.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "a0a683588defcbf01021eb997cd552041a47c14391f189fb3ea6d56904cd8233", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7644dda4df2b7eb86dbb8834d3be9dcd5b14d5d7863bfc6d4689abee547119cc", "generation_seconds_batch": 22.007780354004353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12489078938961029, "target_z": -0.23242186741876764, "ce": 6.070269584655762, "genuineness": 4.457139015197754, "identity": 0.5581088066101074, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/a0a683588defcbf01021eb997cd552041a47c14391f189fb3ea6d56904cd8233.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "a11d5c5576841d94678e0edeeea1f251f47812b011618d2660a85fa18da20964", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6201f580dc5094619f820f5e666a9eb460eb3bfabbca99569550923d99e221d5", "generation_seconds_batch": 31.768644607043825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09230485558509827, "target_z": -0.31250000457734783, "ce": 6.0305562019348145, "genuineness": 4.7081804275512695, "identity": 0.7473646402359009, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/a11d5c5576841d94678e0edeeea1f251f47812b011618d2660a85fa18da20964.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "a25d94d50ef2138b63ee73dfb0a6ecd13827b5b2e7be45901e33f146fef4405f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7a10f2946294caf67af571cea0ff91f6d3f6220700568e7b97046e00ccc35c32", "generation_seconds_batch": 19.204028920968994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1558871567249298, "target_z": -0.15625000228867392, "ce": 6.125868320465088, "genuineness": 4.582659721374512, "identity": 0.5526867508888245, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/a25d94d50ef2138b63ee73dfb0a6ecd13827b5b2e7be45901e33f146fef4405f.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "a28a2abe3cb5f94b7bd9864557917f2c81dc6c5a05138037dd1e9d735ec5f16a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4ae44eb0b40b7d445909ba018ef567170b6f41e21618f44c2de75398f3dec9b7", "generation_seconds_batch": 23.898442486068234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05971892178058624, "target_z": -0.39257814173592803, "ce": 6.0305562019348145, "genuineness": 4.068024158477783, "identity": 0.23320916295051575, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/a28a2abe3cb5f94b7bd9864557917f2c81dc6c5a05138037dd1e9d735ec5f16a.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "a2b2c4e4ef7ba2eee2eac17090f6e21e54b8a5be87374de67fc3523933a67cee", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f626d31d3d351b1993444cedb00a56892a425036a1c411c5eb1669c8fcad5d60", "generation_seconds_batch": 23.971329362946562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22423812747001648, "target_z": 0.011718742847893999, "ce": 5.998785495758057, "genuineness": 4.432034492492676, "identity": 0.5131957530975342, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/a2b2c4e4ef7ba2eee2eac17090f6e21e54b8a5be87374de67fc3523933a67cee.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "a2ef9e60a589acebbdaf683f0e945d6e306177d57b25243df35f3e1fadf7222a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ab1dc33b7996dd84e8ac86a86a1e72d1a56a22ab62b9983403c7f132d98951ef", "generation_seconds_batch": 23.434914151090197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12568557262420654, "target_z": -0.2304687314045244, "ce": 6.324435234069824, "genuineness": 4.381826400756836, "identity": 0.3222831189632416, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/a2ef9e60a589acebbdaf683f0e945d6e306177d57b25243df35f3e1fadf7222a.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": "a36afb9cb52f7ba8079151cd5de76f0bf5273670598ddb3452758dcb12dad89b", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Escribí el número en el sobre.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cfd32899ebfb10ba6a3e7dfa98d6ebe1d399c1ac4ca5d43fc4c8cedf98080303", "generation_seconds_batch": 15.850789993070066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17814096808433533, "target_z": -0.10156248684012496, "ce": 6.141753673553467, "genuineness": 4.65797233581543, "identity": 0.7612090110778809, "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_Bitterness/a36afb9cb52f7ba8079151cd5de76f0bf5273670598ddb3452758dcb12dad89b.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": "a398b41a53bea3368e4754232a95f8998bbe4a2d437eda193e922d4528e0042f", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "facd4c685b219060b7d969340795733a0f6699f4b6cac52f91f13a8ca50d8ab9", "generation_seconds_batch": 23.552643514005467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17257751524448395, "target_z": -0.1152343657022622, "ce": 5.998785495758057, "genuineness": 4.7458367347717285, "identity": 0.7008528709411621, "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_Bitterness/a398b41a53bea3368e4754232a95f8998bbe4a2d437eda193e922d4528e0042f.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "a40fc35a82100af4a7e1b5c651bb3252c2109749472f96fbc026e498f978ecca", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "21f46455732b079dc5da705ff6f1a3b6bd7019e00ae1216352e7f853d4fe9f51", "generation_seconds_batch": 23.349480285076424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19006264209747314, "target_z": -0.07226562972038995, "ce": 5.744620323181152, "genuineness": 4.557555198669434, "identity": 0.6043790578842163, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/a40fc35a82100af4a7e1b5c651bb3252c2109749472f96fbc026e498f978ecca.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "a4434c3f593d5eb7c39d50c854ac000ef3fb9941423d21551d6c7bf8532f4b31", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "352a4835dd172788adc4d06cbe2f7edb876b9aaf466194c60acff94309fe4f28", "generation_seconds_batch": 17.907444561016746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14078636467456818, "target_z": -0.19335936684659916, "ce": 5.33954381942749, "genuineness": 4.231201171875, "identity": 0.5710892677307129, "hypothesis": "La porte 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_Bitterness/a4434c3f593d5eb7c39d50c854ac000ef3fb9941423d21551d6c7bf8532f4b31.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "a4a3efb0d6670dedf93d8bc048b38290f428ed965faed72f4468a8b8d5be21de", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e6eb85cdac01bb47f2fa12c4b06e31f59a9e3edc219df958f1ea32e32b0278ef", "generation_seconds_batch": 16.963649185025133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18449918925762177, "target_z": -0.0859375085825272, "ce": 6.086154937744141, "genuineness": 4.494794845581055, "identity": 0.7898531556129456, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/a4a3efb0d6670dedf93d8bc048b38290f428ed965faed72f4468a8b8d5be21de.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "a50dbdfd499bb917086322c009a290c01af97ea28b59d5c810af64c25f368dfc", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a86cd487b4ab8d008514b507c792c53ecc894f3a021a0003038a758ec4ad6b2d", "generation_seconds_batch": 22.03444226202555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09945786744356155, "target_z": -0.29492187199611547, "ce": 6.205295085906982, "genuineness": 4.344170093536377, "identity": 0.2182137817144394, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/a50dbdfd499bb917086322c009a290c01af97ea28b59d5c810af64c25f368dfc.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": "a5741a5f158ae0bff4fff05b0bfc16a9e2a9ac3c6d05b42fccd76c2881d0c17f", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "77b97e40c3b9b9b4d4564cb4089974468fd7aa62959f1588040c6fa36fa3e435", "generation_seconds_batch": 23.5355758179212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1161482185125351, "target_z": -0.25390625371909514, "ce": 5.015880107879639, "genuineness": 4.017816066741943, "identity": 0.45375752449035645, "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_Bitterness/a5741a5f158ae0bff4fff05b0bfc16a9e2a9ac3c6d05b42fccd76c2881d0c17f.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "a5aaebd82c9607eb5e540f21e6e4b99328019cccfa23d6c84d38ea6241710bac", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f96233529125d3fd28bc48153b2b7f8dd8c8c9c591e4f5876ecbfabe641b542b", "generation_seconds_batch": 23.09461022692267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003289639949798584, "target_z": -0.5312499931339782, "ce": 6.062326908111572, "genuineness": 4.344170093536377, "identity": 0.6089577078819275, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/a5aaebd82c9607eb5e540f21e6e4b99328019cccfa23d6c84d38ea6241710bac.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "a620f4816678fe5437b3dd7b44e711d31b759d42cd21e9061296b299d3961136", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1837443393d0182abbfc68f767cbc52d378f1e91925840f3c1ef428429ae5934", "generation_seconds_batch": 23.44817475392483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22185379266738892, "target_z": 0.005859371423946999, "ce": 5.780362129211426, "genuineness": 4.6203155517578125, "identity": 0.6972123980522156, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/a620f4816678fe5437b3dd7b44e711d31b759d42cd21e9061296b299d3961136.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "a63afdecd3693387be5fd72d4c807bb1b0d8f9fbe08e2296ebadd9afe042baaf", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1e9c69c7c2cb20edf7cfc5e87bcb6fd6185d2144b1d45e57b3b06a289d87ccf7", "generation_seconds_batch": 26.332177647971548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2711300849914551, "target_z": 0.12695314516893894, "ce": 5.371314525604248, "genuineness": 4.13078498840332, "identity": 0.07020843029022217, "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_Bitterness/a63afdecd3693387be5fd72d4c807bb1b0d8f9fbe08e2296ebadd9afe042baaf.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": "a69fafeed0528cff623471b8efebb76e2c4b347e61e9005e6992262b0a17ae09", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0dbe8779ef31962f17aaf91aa339837faf8c5fe9ef5161dac1e38776d9656b68", "generation_seconds_batch": 16.331352062057704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18449918925762177, "target_z": -0.0859375085825272, "ce": 5.895530700683594, "genuineness": 4.758388519287109, "identity": 0.6501038074493408, "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_Bitterness/a69fafeed0528cff623471b8efebb76e2c4b347e61e9005e6992262b0a17ae09.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "a6bb3490194f6f2b7044446da764fd1e823285147726d65cb638a7840ba7928e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d0cd806f2c98badec1c7e56ac02d2614a9a464d5544e1cc0985c2cc92261e84a", "generation_seconds_batch": 22.455489674932323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009426817297935486, "target_z": -0.5624999862679565, "ce": 6.117925643920898, "genuineness": 4.413206577301025, "identity": 0.6328179836273193, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/a6bb3490194f6f2b7044446da764fd1e823285147726d65cb638a7840ba7928e.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "a72ed108eac1d6143121df8913e14cfe739161a5b1aea4246dfef0a68b720ad0", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3acb603925c13f3e729941c2044142d091f30deb12470a2b2425e86ad849beed", "generation_seconds_batch": 16.981136107002385, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1455550342798233, "target_z": -0.18164062399870515, "ce": 6.205295085906982, "genuineness": 4.65797233581543, "identity": 0.5582659244537354, "hypothesis": "Ma 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_Bitterness/a72ed108eac1d6143121df8913e14cfe739161a5b1aea4246dfef0a68b720ad0.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "a7a7d1a981b3169a4af553e46977ad79b6ffbc678696b8ab0c1f51e2bb08b38d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "602dec3853360e1342b7c384a3378e341fdffe2769994236a6f3ec7497f61d38", "generation_seconds_batch": 24.09104685706552, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10025264322757721, "target_z": -0.2929687542912636, "ce": 5.998785495758057, "genuineness": 4.281409740447998, "identity": 0.08021165430545807, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/a7a7d1a981b3169a4af553e46977ad79b6ffbc678696b8ab0c1f51e2bb08b38d.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": "a814ededc4ca4e3fb5d4614a1eba115646f436520660d686803ac26f95c73654", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "db8d5a9fd9fc06d2b6d464ea1be932125be70b1b5f0ceec544ac38c8a537d55e", "generation_seconds_batch": 20.259648323990405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13919681310653687, "target_z": -0.1972656022563029, "ce": 5.967014789581299, "genuineness": 4.68307638168335, "identity": 0.6264021396636963, "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_Bitterness/a814ededc4ca4e3fb5d4614a1eba115646f436520660d686803ac26f95c73654.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "d6ef83220438783d63562650731d10182a11e28854e52bc861e443620febb169", "generation_seconds_batch": 17.516566104022786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06528237462043762, "target_z": -0.3789062628737908, "ce": 6.09409761428833, "genuineness": 4.356721878051758, "identity": 0.7657116651535034, "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_Bitterness/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "heldout-fr-0", "language": "fr", "sentences": [ "Ton message est arrivé après mon départ.", "Je l’ai relu... puis j’ai rangé mon téléphone.", "Dis-moi quand nous pourrons parler." ], "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-0", "key": "a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "7a43d5553423551b0b45dade0fe42a3b806076ec9ae9a15f29a17f6776e6a127", "generation_seconds_batch": 16.60086841590237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13601768016815186, "target_z": -0.2050781463132759, "ce": 6.268836498260498, "genuineness": 4.595211505889893, "identity": 0.7430391311645508, "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_Bitterness/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "a9a974161c34c1285a12b82267239808237d3709d8e8cbfe021eeb09669457d1", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "10621d0e2b57ad7f8e8b494cae67d974129d29284cd2d5881b5bddc941af62e3", "generation_seconds_batch": 23.13287362002302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11137954890727997, "target_z": -0.2656249965669891, "ce": 5.1767191886901855, "genuineness": 4.218649387359619, "identity": 0.528674840927124, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschneben.", "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_Bitterness/a9a974161c34c1285a12b82267239808237d3709d8e8cbfe021eeb09669457d1.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "7bd4619b0d95dde8ae3eaba45aa5c11328e14dd97d5eb93cb0bf7cb2446b5731", "generation_seconds_batch": 15.58396407798864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11535344272851944, "target_z": -0.255859371423947, "ce": 6.459460258483887, "genuineness": 4.300237655639648, "identity": 0.4059458374977112, "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_Bitterness/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "abbe26c0605c126e47da98a71e48429ca491973de209c9fa5dfcc947ad578674", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f4fa2cdc3b257b08fd50622aa21386dd61b06b483860762b54e951e76e0fffc5", "generation_seconds_batch": 22.847386668086983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16780883073806763, "target_z": -0.12695314516893894, "ce": 5.279973983764648, "genuineness": 4.482243061065674, "identity": 0.6571357250213623, "hypothesis": "La porte 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_Bitterness/abbe26c0605c126e47da98a71e48429ca491973de209c9fa5dfcc947ad578674.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "ac3f36be6002506a714c888a934f6a06b33207d55afc4a71f730253bc0236f9f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6200e2c04a8caf35d8e79612413a7939fd55aeb7505da1738d1a010934638daa", "generation_seconds_batch": 22.60861139104236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09309963881969452, "target_z": -0.3105468685631046, "ce": 5.744620323181152, "genuineness": 4.457139015197754, "identity": 0.41583967208862305, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/ac3f36be6002506a714c888a934f6a06b33207d55afc4a71f730253bc0236f9f.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "ac647d87d09ff71922f6603aba6a600860a79ae5aaabe07b7a606b6a50209097", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "bf0fe575511b08293372554eb4b56a71cdd84e395fc19dd0751d6a29888ef7b6", "generation_seconds_batch": 17.671411344897933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10025264322757721, "target_z": -0.2929687542912636, "ce": 5.720792293548584, "genuineness": 4.607763767242432, "identity": 0.746243953704834, "hypothesis": "La porte 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_Bitterness/ac647d87d09ff71922f6603aba6a600860a79ae5aaabe07b7a606b6a50209097.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "ace9e0c242e8fa2d45210d6cd414c27058a0d646573181ad4dcadbb1120264cb", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b90bcd93658f3d9cad150783f37f88a51021a3cb40db425d9a1418e566d7df20", "generation_seconds_batch": 28.662083862931468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18767830729484558, "target_z": -0.07812500114433696, "ce": 5.982900142669678, "genuineness": 4.457139015197754, "identity": 0.4895175099372864, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/ace9e0c242e8fa2d45210d6cd414c27058a0d646573181ad4dcadbb1120264cb.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "450a2d7f286d4d8f7fb7673f6063549d52ecdbf9bcb6daccf18bfc0b98a4ef02", "generation_seconds_batch": 17.027433671057224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08038318157196045, "target_z": -0.34179686169708284, "ce": 6.157639026641846, "genuineness": 4.168440818786621, "identity": 0.6933892369270325, "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_Bitterness/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "ae019cc26bd715f20dbc02e8612e58fa2d62b255343642d7454566ed9647f194", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "310dbe65f7aba0e1280dca789471faf7d26daa4df8e7c3db8f09a622c33d7ac6", "generation_seconds_batch": 17.480037036933936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02474866807460785, "target_z": -0.4785156136996725, "ce": 5.7128496170043945, "genuineness": 4.6705241203308105, "identity": 0.7691643238067627, "hypothesis": "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_Bitterness/ae019cc26bd715f20dbc02e8612e58fa2d62b255343642d7454566ed9647f194.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "13f1bb203b2af85c4a8febad9c57a835a2503a69fd00fa8b10a3cc31c710725d", "generation_seconds_batch": 17.60378365998622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08674140274524689, "target_z": -0.32617188343948506, "ce": 6.372091293334961, "genuineness": 3.998987913131714, "identity": 0.2536274194717407, "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_Bitterness/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "ae37287a5d7963d01674daf751fb43d4b98c606c77b05034e656127bf00b3fbe", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b4cd677ed45f3584fa76f6e37d204ff056388617c6cb8417b4ad47c382e8d961", "generation_seconds_batch": 22.16110268200282, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07879361510276794, "target_z": -0.3457031337255693, "ce": 6.157639026641846, "genuineness": 4.846253395080566, "identity": 0.7411401867866516, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/ae37287a5d7963d01674daf751fb43d4b98c606c77b05034e656127bf00b3fbe.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "ae561fb686753163bfcc6b629550d9534a2ecd1a3f35b3e0946b77b4fc3562f9", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b2151f6b5fb4fbee1cd8a6f80fe112a1ace6545fa942994314f8e56ff051a7c8", "generation_seconds_batch": 24.132053697947413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14714458584785461, "target_z": -0.1777343885890014, "ce": 6.205295085906982, "genuineness": 4.68307638168335, "identity": 0.41254085302352905, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/ae561fb686753163bfcc6b629550d9534a2ecd1a3f35b3e0946b77b4fc3562f9.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "ae595c777587b8608a644a79d37fe94584b50ceb20f3a65fc1264f8e0d664b04", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "17722f3570c35542ebde1fcc24db3c9091f904d941614f128e99ac69309769a5", "generation_seconds_batch": 21.897297795978375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14873415231704712, "target_z": -0.17382811656051492, "ce": 5.403085231781006, "genuineness": 4.6705241203308105, "identity": 0.48708534240722656, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/ae595c777587b8608a644a79d37fe94584b50ceb20f3a65fc1264f8e0d664b04.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "af370c5a6ee75d296e6d628a18a6b93d6efd2ed17ce8e95b381ccdec5e8d0a54", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "71bf8b9ec132065d2a0bd468d0307788dd2da9873936c34e8fc2f8078cc4310f", "generation_seconds_batch": 22.871757179964334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1368124783039093, "target_z": -0.20312497368024993, "ce": 5.824047088623047, "genuineness": 4.570107460021973, "identity": 0.7704406976699829, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre, nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/af370c5a6ee75d296e6d628a18a6b93d6efd2ed17ce8e95b381ccdec5e8d0a54.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": "b0e57a9ae61a1ee1d360144bac387a8bca265ee912dff833b295908e1bba7545", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5915f42fc2b1e12a3dfbcbfc143acc93d7567bb446677f1c03777542ca82baca", "generation_seconds_batch": 24.236544721992686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15509238839149475, "target_z": -0.15820310168413443, "ce": 6.022613525390625, "genuineness": 4.143336772918701, "identity": 0.45868396759033203, "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_Bitterness/b0e57a9ae61a1ee1d360144bac387a8bca265ee912dff833b295908e1bba7545.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "b151adfe066965796d855c1cf6cf56bb17b09eb17bf59e73d430c02d515cd412", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "81584bf973daed76700203d17e6237dc78ff9c2167b59bdb3d34c6c5150ce6c3", "generation_seconds_batch": 16.620169023051858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08435706794261932, "target_z": -0.3320312548634321, "ce": 5.7406487464904785, "genuineness": 4.494794845581055, "identity": 0.58636873960495, "hypothesis": "La porte 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_Bitterness/b151adfe066965796d855c1cf6cf56bb17b09eb17bf59e73d430c02d515cd412.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "b1864bd43e60d16deb25f25f1e75404e818b20227d1113f3f485c32e71f540dc", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "048f09e3c0e00ff409a596e94a82345655f0bfe39c1e53ff69af5b2da37563f1", "generation_seconds_batch": 22.56569595192559, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15827149152755737, "target_z": -0.15039063086472693, "ce": 6.252951145172119, "genuineness": 4.557555198669434, "identity": 0.8108447194099426, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b1864bd43e60d16deb25f25f1e75404e818b20227d1113f3f485c32e71f540dc.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "b19376530b35796a9c8bde091bbd67e18fa7a95cb893105d427be076f82afb3a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ff25d7ee91fa08bfae561bb4c3a2df2dc1104b79dfaf1e4caf33f3fbed89983e", "generation_seconds_batch": 24.806034008972347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16621927917003632, "target_z": -0.1308593805786427, "ce": 5.061550617218018, "genuineness": 4.281409740447998, "identity": 0.6140811443328857, "hypothesis": "la puerta sigue abierta. he dejado tu abrigo sobre la silla, dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b19376530b35796a9c8bde091bbd67e18fa7a95cb893105d427be076f82afb3a.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "b1e754b341eaeeefce4a2456b9e56a252d84080a56797e1590484aacf2faa85e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "85c23bbf9e01116b2f18135b9489d5547d94f1d2ab81ce638aca2ba99a13ac31", "generation_seconds_batch": 23.582927935989574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1423759162425995, "target_z": -0.1894531314368954, "ce": 5.5539960861206055, "genuineness": 4.432034492492676, "identity": 0.6416288018226624, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b1e754b341eaeeefce4a2456b9e56a252d84080a56797e1590484aacf2faa85e.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": "b25955f2463136899b42af704cabb350e00321d2be9b83709253a188b842400f", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "54ca6562a7b40403c4f6f09c2926dc110cbda609e932366ca5b42db8012770b4", "generation_seconds_batch": 17.555713724112138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14158114790916443, "target_z": -0.19140623083235592, "ce": 5.744620323181152, "genuineness": 4.7834930419921875, "identity": 0.827347993850708, "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_Bitterness/b25955f2463136899b42af704cabb350e00321d2be9b83709253a188b842400f.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "b27b642b2676a532950f56d3fc05fac6332de0075dcf094660d7db7ff80794b6", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bfecff3242eb922e88b2279f39b81022daf5ca986e8bb7ebb3683e1b96528bd3", "generation_seconds_batch": 27.326148562016897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10502132028341293, "target_z": -0.28124999313397825, "ce": 6.078212261199951, "genuineness": 4.093128204345703, "identity": 0.14647330343723297, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b27b642b2676a532950f56d3fc05fac6332de0075dcf094660d7db7ff80794b6.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "b29f353bc59207fb3af6a28e63ee95c6c022ea2aa0d7e37794ebf4afb5d29da9", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5e7ff8934a12c907842142b7b6a1a2d327b7c668cdaef5fe95d4e275e8a2efb6", "generation_seconds_batch": 22.896398673998192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04859203100204468, "target_z": -0.4199218628414198, "ce": 5.728734970092773, "genuineness": 4.162164688110352, "identity": 0.7375022768974304, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b29f353bc59207fb3af6a28e63ee95c6c022ea2aa0d7e37794ebf4afb5d29da9.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "b2c621259e0a2e7cbbc7c989ed19c049baccbc322c34f7e1ded72ad15d647c07", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c05519600d364505799007d349a8005ad677cdd425b617bf917ae1acd86deac4", "generation_seconds_batch": 24.12783022900112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02792777121067047, "target_z": -0.470703142880265, "ce": 6.403861999511719, "genuineness": 4.482243061065674, "identity": 0.5648137927055359, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b2c621259e0a2e7cbbc7c989ed19c049baccbc322c34f7e1ded72ad15d647c07.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "b2d82322ee0b55fda0acfb913e932b72ca35ee0d447431eea6aac1556fe485c8", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8ea315ff3a47de043de9872368f07af8984922a910a412fe067f9785905c8015", "generation_seconds_batch": 23.7612807599362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09945786744356155, "target_z": -0.29492187199611547, "ce": 6.260893821716309, "genuineness": 4.413206577301025, "identity": 0.45140600204467773, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b2d82322ee0b55fda0acfb913e932b72ca35ee0d447431eea6aac1556fe485c8.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "b312277cd76b17fb33ec83682293c1c75206daa68cef9ce2031b180c6166d09a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0cd7b3a8de84bd1194e05ae26adf9dc9ffaffe56c3dbd9c9301c734e504164a2", "generation_seconds_batch": 23.512912012985907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11853255331516266, "target_z": -0.24804688229514812, "ce": 5.959072113037109, "genuineness": 4.595211505889893, "identity": 0.6130688786506653, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b312277cd76b17fb33ec83682293c1c75206daa68cef9ce2031b180c6166d09a.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "b366be6bd8cab3af29482c257ee61fc6dc230ed44046ca6bd9b1cd1d220e4e6b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e8751f44746bfa903fd57046a35aeb9c161af34313d3d7f5e71df9791b404040", "generation_seconds_batch": 15.509391902014613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09151007235050201, "target_z": -0.3144531405915911, "ce": 6.133810997009277, "genuineness": 4.821148872375488, "identity": 0.6907257437705994, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b366be6bd8cab3af29482c257ee61fc6dc230ed44046ca6bd9b1cd1d220e4e6b.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "b36fcbc29e7243c775a6f02885791d37e29b4a76b93c1969a2bae2edc1aee331", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "49983ddb17f00226ec53601dd3d95ed5b9f6449aa768ede680cdaf00fa558806", "generation_seconds_batch": 24.38816361106001, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12091689556837082, "target_z": -0.24218749256180977, "ce": 5.2065043449401855, "genuineness": 4.231201171875, "identity": 0.39188098907470703, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b36fcbc29e7243c775a6f02885791d37e29b4a76b93c1969a2bae2edc1aee331.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": "b374f0391f23f11f0271ef8d86ee79330d963013c035c1936207c1ebaf1d97dd", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0a2f1df2a0b3f8293992a3c9d8ef54f2249d20425026e8f03de2811dde956f44", "generation_seconds_batch": 24.557670356007293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.117737777531147, "target_z": -0.25, "ce": 6.181467056274414, "genuineness": 4.607763767242432, "identity": 0.6749220490455627, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekkast. We zetten het na de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b374f0391f23f11f0271ef8d86ee79330d963013c035c1936207c1ebaf1d97dd.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "b3af0f7165393e2d4f78315d8bccf72a5aac3ec1e90b521be4f5f4fcbba6d38d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ea3f68a53ed1caa94d679b7b951d481f9eb2f32b8ba4625f14ece72e6b734270", "generation_seconds_batch": 21.51424006803427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02633821964263916, "target_z": -0.47460937828996874, "ce": 6.046441555023193, "genuineness": 4.607763767242432, "identity": 0.6187038421630859, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b3af0f7165393e2d4f78315d8bccf72a5aac3ec1e90b521be4f5f4fcbba6d38d.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "b3e1a641ef956b80d7c9e4aacdc28d6a328e3a5b11264ba331a5c92ccb890459", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2c6e11f2749b3bc5ad482028b20048226a6b5f782a43ca47a6f53c1361eb930b", "generation_seconds_batch": 27.36135235801339, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.036670342087745667, "target_z": -0.44921875657993754, "ce": 6.173524379730225, "genuineness": 4.432034492492676, "identity": 0.5788396596908569, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b3e1a641ef956b80d7c9e4aacdc28d6a328e3a5b11264ba331a5c92ccb890459.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "b3eea30a6d5e0d83864c739ae9ed0b463330b56f0b6f1bad3f7a2d8bed055129", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6733c8d4240915df87cdcb38ff7c06ec3887a7b4bb45567843d1c1a200e64c37", "generation_seconds_batch": 23.049984700977802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19165220856666565, "target_z": -0.06835935769190347, "ce": 6.149696350097656, "genuineness": 4.6705241203308105, "identity": 0.5816597938537598, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b3eea30a6d5e0d83864c739ae9ed0b463330b56f0b6f1bad3f7a2d8bed055129.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "b40b00c11af7ebb8ab36141b052dc8da4a9a8c26b3b652633e31dab75a25f237", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8a810c22413105870ed6b108fd607ff2d5eca47b99ea2f14bd0fdbf5cb79e745", "generation_seconds_batch": 16.594955797074363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.028501510620117188, "target_z": -0.6093749942783152, "ce": 6.372091293334961, "genuineness": 4.68307638168335, "identity": 0.45495402812957764, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b40b00c11af7ebb8ab36141b052dc8da4a9a8c26b3b652633e31dab75a25f237.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "b626ac93bc58eeedb5d8b5a2158b6d5c0a8e949af5e8c70b044cc911e3da2dbb", "generation_seconds_batch": 16.701746012899093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0795883983373642, "target_z": -0.3437499977113261, "ce": 6.141753673553467, "genuineness": 4.444586753845215, "identity": 0.5145555138587952, "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_Bitterness/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "b4686974398212b541c7b269645af372f27a2e754113815ab42bd282ec65da2f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "10ec8a2eae18314d508330a40eeb0167a17dcfa009b56874a55a6715a1f1af1b", "generation_seconds_batch": 27.091077251941897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23695458471775055, "target_z": 0.04296873598187224, "ce": 5.677107334136963, "genuineness": 4.444586753845215, "identity": 0.1962747573852539, "hypothesis": "Ik heb een klein doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.1111111111111111, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b4686974398212b541c7b269645af372f27a2e754113815ab42bd282ec65da2f.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "b47855e58b506c6f675ae681fb40c018878cc2bf7dd6fcc0f53b6229d64b38e6", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f693b5364c6cda725b0b312b483b6838f27cfa4c7ec4fda7015787d7e35929c7", "generation_seconds_batch": 16.7087722819997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.018964171409606934, "target_z": -0.5859375085825272, "ce": 6.157639026641846, "genuineness": 4.557555198669434, "identity": 0.41944390535354614, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b47855e58b506c6f675ae681fb40c018878cc2bf7dd6fcc0f53b6229d64b38e6.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "b47db98cbe38f0611c94e5f17ad8c457880f5a55d0816bd7da117309a8997411", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8e326ba1ad91836501d81d14a4ce16ec05388909d11165c156139eedf6b782c3", "generation_seconds_batch": 24.722081487998366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11058476567268372, "target_z": -0.26757813258123236, "ce": 6.0305562019348145, "genuineness": 4.482243061065674, "identity": 0.6236507892608643, "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_Bitterness/b47db98cbe38f0611c94e5f17ad8c457880f5a55d0816bd7da117309a8997411.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "b4f160739b9a8fd788c6bf8031c5ae862e075f121862cbeb5518af103e7b1747", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5417418d78844f01c47319ddec5945ef6514206d9bf858360182f321380c822e", "generation_seconds_batch": 16.963649185025133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17655140161514282, "target_z": -0.10546875886861144, "ce": 5.9431867599487305, "genuineness": 4.557555198669434, "identity": 0.7941116094589233, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b4f160739b9a8fd788c6bf8031c5ae862e075f121862cbeb5518af103e7b1747.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "b61fa2444629c4862a68dc8defe8c50fd0ba2c2a1d3bc00c017263877ae000be", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9c5c0b475fab3f0d2a23880ab445e3d527d324e67534a4a252ab4ca5cdfe0e07", "generation_seconds_batch": 23.709817023016512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19642087817192078, "target_z": -0.05664061484400948, "ce": 6.109982967376709, "genuineness": 4.256305694580078, "identity": 0.44320279359817505, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b61fa2444629c4862a68dc8defe8c50fd0ba2c2a1d3bc00c017263877ae000be.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "b6b1fe7d2a25c115be66b2d3a537deab945957dbc058f2e101f4a598ddbdcd8c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2d325c8c08e8f7856e8afe54b8e054e870a4eb2806c37a737f5015afba9805c7", "generation_seconds_batch": 21.182747012004256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0899205207824707, "target_z": -0.3183593760012948, "ce": 6.022613525390625, "genuineness": 4.143336772918701, "identity": 0.3115866482257843, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b6b1fe7d2a25c115be66b2d3a537deab945957dbc058f2e101f4a598ddbdcd8c.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "b7043b59b395f4f46d9be79ea1611b77ea7835a90074d030bdd891fd739ca688", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7e24f004df33576a95a000457bdb71111f855fea32d44e232641c3515ec790dc", "generation_seconds_batch": 18.12146454595495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10422653704881668, "target_z": -0.2832031291482215, "ce": 6.260893821716309, "genuineness": 4.3127899169921875, "identity": 0.3178660273551941, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b7043b59b395f4f46d9be79ea1611b77ea7835a90074d030bdd891fd739ca688.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": "b79efb4ace0a3bdc1b5d1e47e3cedf5e7971f1506b3aacc86cbd8a028508dea9", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fb5a9d8b8a61bd53172e95bf09378548734f7db2c113ffd78772c53bcbb82f81", "generation_seconds_batch": 16.332715074997395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09230485558509827, "target_z": -0.31250000457734783, "ce": 5.959072113037109, "genuineness": 4.306513786315918, "identity": 0.3967435657978058, "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_Bitterness/b79efb4ace0a3bdc1b5d1e47e3cedf5e7971f1506b3aacc86cbd8a028508dea9.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "b7b946c144adc6bf27119dac6fe42d185d315d4fcd96af4ef946a5fd1bfe83fc", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7a7589fda6840bb515cad2a5ffad8a191f9ce9b73a6a2f2647795b3ef8669fdc", "generation_seconds_batch": 23.85233663499821, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37763041257858276, "target_z": 0.3886718330886588, "ce": 5.43088436126709, "genuineness": 3.760498285293579, "identity": 0.4703952372074127, "hypothesis": "Ik heb een kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b7b946c144adc6bf27119dac6fe42d185d315d4fcd96af4ef946a5fd1bfe83fc.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "b7fed3fc68334cbdb8645f488842a57c273d3fdb2c7be60589123dab409d9e36", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "edd8b6a7efb5017dd78902947884f36c4ce5bc8a11d000e059f8c02a530ef2c9", "generation_seconds_batch": 21.51424006803427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.001700073480606079, "target_z": -0.5351562651624647, "ce": 6.078212261199951, "genuineness": 4.7332844734191895, "identity": 0.6712483167648315, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b7fed3fc68334cbdb8645f488842a57c273d3fdb2c7be60589123dab409d9e36.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "b932344ca00dd2c85130032bb86bcf59fa614c089dc380d58fae4346adcc3510", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9afb57ec2223ce62c3ddc15b014a6d0ae7861cadd61d70a4e1bd0f3d702a0dbd", "generation_seconds_batch": 23.785309836035594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11455865949392319, "target_z": -0.25781250743819023, "ce": 6.0305562019348145, "genuineness": 4.432034492492676, "identity": 0.581375002861023, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/b932344ca00dd2c85130032bb86bcf59fa614c089dc380d58fae4346adcc3510.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": "b93f358f0ab749ab224de20515e30be80098ce6bda470e9e1f8f57fe4b0e0e20", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b5d7eab0810a095a3d25959018df2c13146a17f028199b5a5cf730ccfde9e46e", "generation_seconds_batch": 22.025799817987718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7662771940231323, "target_z": 1.3437498878549778, "ce": 5.974957466125488, "genuineness": 4.21237325668335, "identity": 0.3147888779640198, "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_Bitterness/b93f358f0ab749ab224de20515e30be80098ce6bda470e9e1f8f57fe4b0e0e20.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "ba40a2c885b3d998242acd0edadb63938c4a167e5a5337ea852e5bed3825281b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "53ff77f9b2f36fbbe74c6d35c3758152be9280afd6861ffa06988e93e08dfe65", "generation_seconds_batch": 25.589102189056575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20754778385162354, "target_z": -0.029296857119735, "ce": 5.689021587371826, "genuineness": 4.457139015197754, "identity": 0.49439477920532227, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/ba40a2c885b3d998242acd0edadb63938c4a167e5a5337ea852e5bed3825281b.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "aa2c22379630c24752e821a3e2c3fdcfbcc515cd4c78fb6c9c1887f7eec05599", "generation_seconds_batch": 16.37285480706487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022364333271980286, "target_z": -0.48437498512361954, "ce": 6.205295085906982, "genuineness": 4.381826400756836, "identity": 0.7172353267669678, "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_Bitterness/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "ba8f6aacbfb8dd26c1a6ae69d0ee13a12cadb934dc2cf121114c0ec63f2e393f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f94c8547d56b03dc9e224c2f9718c4c079229ea9add6de5508f5cd5dc6c9664c", "generation_seconds_batch": 22.306231147027574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10820043087005615, "target_z": -0.27343750400517935, "ce": 4.883832931518555, "genuineness": 3.8169827461242676, "identity": 0.4334350824356079, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/ba8f6aacbfb8dd26c1a6ae69d0ee13a12cadb934dc2cf121114c0ec63f2e393f.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "bb061474d1df854af2820f4b43772f7548c9fbc0faddffc5f228254523739c53", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "be4cdc69d5f5b967cd54bed24353321c060399db3263719e56e72a630b3a3d5c", "generation_seconds_batch": 24.0646369230235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.012605935335159302, "target_z": -0.5703124937061467, "ce": 6.284721851348877, "genuineness": 4.494794845581055, "identity": 0.355430543422699, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/bb061474d1df854af2820f4b43772f7548c9fbc0faddffc5f228254523739c53.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "bb3f5a6e15b0c6721412c8de8507a2f90a862e31f8f30673e911c411de7a2dfd", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "764b5a257c898797a92ecde5f69f1f0517b92eb8b5588bb103bd18974437f754", "generation_seconds_batch": 28.29528961190954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2818595767021179, "target_z": 0.1533202799579177, "ce": 5.9431867599487305, "genuineness": 4.545003414154053, "identity": 0.5000545382499695, "hypothesis": "Ik heb het kleine doosje gewonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/bb3f5a6e15b0c6721412c8de8507a2f90a862e31f8f30673e911c411de7a2dfd.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "bb51fe19baed666d504ea0ad990d7d5e263f9ee1909f859b6fa574754c2e8e5c", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4b58d25681938fa636238496bf2b2fe07236be179935119f26ac157a9857b081", "generation_seconds_batch": 17.219643565942533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07164061069488525, "target_z": -0.3632812479974103, "ce": 6.157639026641846, "genuineness": 4.65797233581543, "identity": 0.6402677893638611, "hypothesis": "La porte 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_Bitterness/bb51fe19baed666d504ea0ad990d7d5e263f9ee1909f859b6fa574754c2e8e5c.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "bb8e3ce250c73f639d8d17ebf37e56d5711967672ae07d14113387c53290ae55", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7754f36057e47a0a1c020ecda443905c09bab4db650fe2083b3ec2578a0757c5", "generation_seconds_batch": 22.716509531019256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17655140161514282, "target_z": -0.10546875886861144, "ce": 5.585766792297363, "genuineness": 4.331617832183838, "identity": 0.7023503184318542, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/bb8e3ce250c73f639d8d17ebf37e56d5711967672ae07d14113387c53290ae55.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "bbbf284aca09dc2ed15f16fe81a1d0c1480205d91c5ac18a196731a1208e7aaf", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6349049cdfd15838492b9419faaaf6a7af97ac48d143a3866aa3765ae41649bf", "generation_seconds_batch": 17.112980129080825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02792777121067047, "target_z": -0.470703142880265, "ce": 6.070269584655762, "genuineness": 4.557555198669434, "identity": 0.7835471630096436, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/bbbf284aca09dc2ed15f16fe81a1d0c1480205d91c5ac18a196731a1208e7aaf.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "bc736aa801c21d227f687859ec361666e3cb85d44b1e8141b6057c93f094d684", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e8b5fcbfec35c84bd6b69f64d5a5fd8a9c935242f0476456e8ce2a388b7fffa4", "generation_seconds_batch": 23.185873958980665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19642087817192078, "target_z": -0.05664061484400948, "ce": 5.990842819213867, "genuineness": 4.362998008728027, "identity": 0.504912257194519, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/bc736aa801c21d227f687859ec361666e3cb85d44b1e8141b6057c93f094d684.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": "bcc4c32b340ef290d66e612e6d46d87096c068c0481fcd1980c6c2b653211ca6", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "100c2d9212a63c29b7b18b17f93c1f653ac1e5419f1f4299d2fef7f4356f3a26", "generation_seconds_batch": 23.902683955035172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1423759162425995, "target_z": -0.1894531314368954, "ce": 5.935244083404541, "genuineness": 4.6203155517578125, "identity": 0.5758339166641235, "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_Bitterness/bcc4c32b340ef290d66e612e6d46d87096c068c0481fcd1980c6c2b653211ca6.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "bcd90f68c64257ff668719eb6b7ec421236b2401d26f5eb5a849fbdc85b4bc18", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "be9ef27184fdca6dc56f5034b29191a5754c84b7b040b2514fdb3f27d3c05be4", "generation_seconds_batch": 23.153591564972885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1089952141046524, "target_z": -0.2714843679909361, "ce": 5.792276382446289, "genuineness": 4.65797233581543, "identity": 0.7106403112411499, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/bcd90f68c64257ff668719eb6b7ec421236b2401d26f5eb5a849fbdc85b4bc18.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": "bce88708df3b044449a90ac7dd66660691f33b8664220b5443d61688e940cf8c", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Someone moved the little blue chair.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "07cc506ef33c0a52ac98b3638169f3ca130010c301deb63f6c71178e5800fb5c", "generation_seconds_batch": 17.318436736939475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16939839720726013, "target_z": -0.12304687314045244, "ce": 6.435632705688477, "genuineness": 4.833701133728027, "identity": 0.35286226868629456, "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_Bitterness/bce88708df3b044449a90ac7dd66660691f33b8664220b5443d61688e940cf8c.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "bcfe0b59eea0e84607949a27c12f1f1142273175770856439898f8f8d03f4f13", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3f5a1a052d4ab2c7d10d5315e9ab43ca610ba5045aeb06d77b24d417bf7275bd", "generation_seconds_batch": 15.08694672002457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19483131170272827, "target_z": -0.06054688687249596, "ce": 5.95112943649292, "genuineness": 4.833701133728027, "identity": 0.5819522142410278, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/bcfe0b59eea0e84607949a27c12f1f1142273175770856439898f8f8d03f4f13.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "bd60c5f40f6135039d32acc419c84dfa22ea25fb9ed45f578124a3ac86f9a60e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ac6539d98b8d12d02132c2d127916bd1ae8bb35405fcb403baabec939f1fc84a", "generation_seconds_batch": 21.592318866983987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18290963768959045, "target_z": -0.08984374399223095, "ce": 5.816103935241699, "genuineness": 4.7332844734191895, "identity": 0.296448677778244, "hypothesis": "La porte 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_Bitterness/bd60c5f40f6135039d32acc419c84dfa22ea25fb9ed45f578124a3ac86f9a60e.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "bd7a53e0d485da8cbdc901b49d963282fc5404bae665dcbbe44427c1ecba203f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c8b46a6dad6baa577284af95b80ca4648fc803dba1e53aff7daa0989c07f0843", "generation_seconds_batch": 23.90710644493811, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.062103271484375, "target_z": -0.3867187336931983, "ce": 6.133810997009277, "genuineness": 4.7081804275512695, "identity": 0.6084263324737549, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/bd7a53e0d485da8cbdc901b49d963282fc5404bae665dcbbe44427c1ecba203f.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "bdcec393f29c10dd28033f6d65965c9ade97e45311575f52f63b46c5ac12cadb", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "64ccd6b912c4f07b1c67122753acb41b22ff19e4955809f76249d1971e11f857", "generation_seconds_batch": 22.799222811008804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15986105799674988, "target_z": -0.14648435883624045, "ce": 5.95112943649292, "genuineness": 4.7081804275512695, "identity": 0.47096025943756104, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/bdcec393f29c10dd28033f6d65965c9ade97e45311575f52f63b46c5ac12cadb.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "bdd9c58acad651b6cae2b49a2d2e31e4a1bd457e43a46fb3a229a929f42adcac", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7c40a753cf0038110664b872b163ff7f864cbc6b74d43f351ba943a39df972f0", "generation_seconds_batch": 24.198599909897894, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10104742646217346, "target_z": -0.2910156182770204, "ce": 5.974957466125488, "genuineness": 4.758388519287109, "identity": 0.7833285331726074, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/bdd9c58acad651b6cae2b49a2d2e31e4a1bd457e43a46fb3a229a929f42adcac.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "be2bcf3da9d5f681ff26161b5f482f92f2501c5c9a89f3655ca608f061746d90", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d7cda76837b778927237df7244ce1e6778039f8fc378c5c83f604c8efe3a9309", "generation_seconds_batch": 22.705748685984872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006247714161872864, "target_z": -0.554687515448549, "ce": 5.998785495758057, "genuineness": 4.607763767242432, "identity": 0.3644036650657654, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/be2bcf3da9d5f681ff26161b5f482f92f2501c5c9a89f3655ca608f061746d90.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "be84a45aa53c18f88f2341c49d7c4f98cd6b7c7b602436a0b82b10f12660edf4", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ffcc30101c7c07d3a942e22be30492f4bb466d0c3f40272b156041d9af620f7f", "generation_seconds_batch": 23.434914151090197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1280699074268341, "target_z": -0.2246093599805774, "ce": 5.990842819213867, "genuineness": 3.6914620399475098, "identity": 0.2232685685157776, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/be84a45aa53c18f88f2341c49d7c4f98cd6b7c7b602436a0b82b10f12660edf4.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": "beebe67393a1b06fbdd709011e65071ffb17bc677ffaca9b165a7b41bc7918a4", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Someone moved the little blue chair.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6783758399d0254a248bffe25ba7cf58ec8b45eb1b6de54036ee4c2b82faa091", "generation_seconds_batch": 25.658768982975744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12489078938961029, "target_z": -0.23242186741876764, "ce": 6.41180419921875, "genuineness": 4.65797233581543, "identity": 0.2520332336425781, "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_Bitterness/beebe67393a1b06fbdd709011e65071ffb17bc677ffaca9b165a7b41bc7918a4.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "bf367521413e61d90c718d2f272b780fa6cb56254cff74b689c85bc6e08e4cd0", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5ffe983eac0b862e77d8ecd8b6394bd12f07f91c2f9ebd090691ffd5ba41cd2f", "generation_seconds_batch": 23.35575611004606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018390432000160217, "target_z": -0.494140628576053, "ce": 6.141753673553467, "genuineness": 4.375550270080566, "identity": 0.5985462665557861, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/bf367521413e61d90c718d2f272b780fa6cb56254cff74b689c85bc6e08e4cd0.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "bf9394228cc66249e1d47c660da66228b0121012d2aad20b8030388c067cc1d2", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9fa10463003f4a6a72d812e7e47e9132a9ff97b94ac0c66ce5b187a83f8f5470", "generation_seconds_batch": 18.31573661090806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06687194108963013, "target_z": -0.37499999084530433, "ce": 5.839932441711426, "genuineness": 4.7834930419921875, "identity": 0.7798894643783569, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/bf9394228cc66249e1d47c660da66228b0121012d2aad20b8030388c067cc1d2.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "bfb8f23675c537b43595a371fcd23275c00c7a27e13d96cc3862b1fcea7e05d9", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e1b5a0706dc8ddac72db4c297d936140fd0538ed836e406f43cceb6cdfbfb7de", "generation_seconds_batch": 25.190924953087233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06925627589225769, "target_z": -0.36914061942135734, "ce": 6.427689552307129, "genuineness": 4.6956281661987305, "identity": 0.7320447564125061, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/bfb8f23675c537b43595a371fcd23275c00c7a27e13d96cc3862b1fcea7e05d9.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "c0939dc075773514de0fb2e06ec395bf0f8cae93f9a73d279c59a5e2c21f5b22", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "96699551ef8b7e53ddce66309eba09a0005e2e76d659e35252eb48a86e8c18ae", "generation_seconds_batch": 28.313874340965413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08912573754787445, "target_z": -0.32031251201553806, "ce": 6.1894097328186035, "genuineness": 4.582659721374512, "identity": 0.5724542140960693, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt, sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c0939dc075773514de0fb2e06ec395bf0f8cae93f9a73d279c59a5e2c21f5b22.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "c16d227a0b967d739bdf9a87103a5573a5fe0a79191b43e975e0f296b3be7349", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "614eea8e9ad2561141ea6d8af2eee20d79032c7bf3c166bd0d5b82a0f96e090c", "generation_seconds_batch": 22.600528057082556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13045424222946167, "target_z": -0.2187499885566304, "ce": 6.133810997009277, "genuineness": 4.306513786315918, "identity": 0.39841872453689575, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c16d227a0b967d739bdf9a87103a5573a5fe0a79191b43e975e0f296b3be7349.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "c184a376dd4a573224e97c012067de6e5812de404589a06c7cf8dec0524d00c3", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6279ca5abf0b12b6a609340754b054d66f3d6929978ac253f6ad1fb9de314e23", "generation_seconds_batch": 17.661625984008424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05653981864452362, "target_z": -0.40039061255533553, "ce": 6.23706579208374, "genuineness": 4.65797233581543, "identity": 0.5051072239875793, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c184a376dd4a573224e97c012067de6e5812de404589a06c7cf8dec0524d00c3.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "c1e9b32c4f8e98be007be2a710a2e442eaa9dbd49871714b3eec2c2e53e0961f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "50691f3e3d2cebe379b4045dc5790c1a338ea86b86216f6cc9ed91d109879698", "generation_seconds_batch": 23.84346440806985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15111848711967468, "target_z": -0.16796874513656793, "ce": 5.450741291046143, "genuineness": 4.406930446624756, "identity": 0.5971605181694031, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás libre.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c1e9b32c4f8e98be007be2a710a2e442eaa9dbd49871714b3eec2c2e53e0961f.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "c1f9c099a58a8daae7d42f0dca305ca0bb5eb7445044d27cb0b876d316e73c88", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "98a5c6ba86f40c01dc25c105d64d6028b94eecdcf0fce7a5d69724d3f432f985", "generation_seconds_batch": 23.919414627016522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21231645345687866, "target_z": -0.017578114271841, "ce": 6.022613525390625, "genuineness": 4.68307638168335, "identity": 0.537885308265686, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c1f9c099a58a8daae7d42f0dca305ca0bb5eb7445044d27cb0b876d316e73c88.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "c2266b7906e64b083fc49890f48cee15f29227c06b9699fb5982c84014e30d04", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1a819ba90f572cd5f2de67c05dd33dca5d4c235d5d2759513fb6bd15d7b5e472", "generation_seconds_batch": 15.656238801078871, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19165220856666565, "target_z": -0.06835935769190347, "ce": 5.847874641418457, "genuineness": 4.2249250411987305, "identity": 0.5030712485313416, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c2266b7906e64b083fc49890f48cee15f29227c06b9699fb5982c84014e30d04.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "c240b572d80a05561e7ad93f59cba1e15aa5c80c83ccfeb25e019990b5d6be99", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8645c14d0e08e803eeda9c294ffa763c06fcdc3169e6097c80494469b837116a", "generation_seconds_batch": 16.90050096390769, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20595821738243103, "target_z": -0.03320312914822148, "ce": 5.871703147888184, "genuineness": 4.532451152801514, "identity": 0.21652033925056458, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c240b572d80a05561e7ad93f59cba1e15aa5c80c83ccfeb25e019990b5d6be99.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "c27463d497835fa1df68bf1ca0e53cbb78287d0f50bee1bd7a9ea78754f18115", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "714c8fa54f7ce95f7ea5ace9372a644ea6944aaa20fbf41d29952db4aef478d3", "generation_seconds_batch": 22.52820741897449, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15111848711967468, "target_z": -0.16796874513656793, "ce": 6.054384231567383, "genuineness": 4.7332844734191895, "identity": 0.7546920776367188, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c27463d497835fa1df68bf1ca0e53cbb78287d0f50bee1bd7a9ea78754f18115.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "c2b1db7433ac450b92fc020653bf0446b6216ee49c5b252883833c2fa52363e5", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e043dc81fc38f5ba1c0117700a0a333ac6aafc5eb5ae04da9161b29746db002c", "generation_seconds_batch": 16.852264299057424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12409600615501404, "target_z": -0.23437500343301088, "ce": 6.086154937744141, "genuineness": 4.7081804275512695, "identity": 0.5094771385192871, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c2b1db7433ac450b92fc020653bf0446b6216ee49c5b252883833c2fa52363e5.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "c2b9c640fd9c036d50fc95d9c0868a764c68a3378575ee2d045ff382bc4263d8", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "58395462ad33a00c5daf7e29a5a576c50a8ac6362fd657e7917db7c443dab75f", "generation_seconds_batch": 18.416059608920477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19562609493732452, "target_z": -0.05859375085825272, "ce": 5.458683967590332, "genuineness": 4.394378662109375, "identity": 0.3158557415008545, "hypothesis": "J'ai trouvé la 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_Bitterness/c2b9c640fd9c036d50fc95d9c0868a764c68a3378575ee2d045ff382bc4263d8.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": "c2bfd28ced8bce51210f38adbd3ed9c85bf9f79ba0824c073ef0b63f01958f19", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Escribí el número en el sobre.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8b13c9224bbf68f69a30a72d3eb89efcb15cd0e42acc44b92b02b297d0100294", "generation_seconds_batch": 24.154926970019005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21390600502490997, "target_z": -0.01367187886213724, "ce": 6.070269584655762, "genuineness": 4.419482707977295, "identity": 0.6826547384262085, "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_Bitterness/c2bfd28ced8bce51210f38adbd3ed9c85bf9f79ba0824c073ef0b63f01958f19.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "c33150f127f1f17ffcb9df6066c81f16f885143d3a7fa048015321ec7587e765", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9efd3643dedfce23f0fd4c0af393ce2025112542e68cb2ed6d685da703c45082", "generation_seconds_batch": 21.74320991395507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09309963881969452, "target_z": -0.3105468685631046, "ce": 6.141753673553467, "genuineness": 4.645420074462891, "identity": 0.7898324728012085, "hypothesis": "La porte 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_Bitterness/c33150f127f1f17ffcb9df6066c81f16f885143d3a7fa048015321ec7587e765.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "c3475b6dcd5618f79ed3c696bdd3552303f0c811e3e1b28f97d539f4b4ab3bde", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9a30fe3350fa6bb051ef91c9f92c63e189d117f283079edfc83afa4183de877c", "generation_seconds_batch": 22.516891865991056, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05653981864452362, "target_z": -0.40039061255533553, "ce": 6.197352409362793, "genuineness": 4.030367851257324, "identity": 0.34345996379852295, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c3475b6dcd5618f79ed3c696bdd3552303f0c811e3e1b28f97d539f4b4ab3bde.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "95346addb1877e25454c22f476cbf789a0f5f6638417c3c74363b1b836230001", "generation_seconds_batch": 16.50387060898356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08594663441181183, "target_z": -0.3281249828349456, "ce": 6.078212261199951, "genuineness": 4.356721878051758, "identity": 0.6248162984848022, "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_Bitterness/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "c3a9f8f19c28ffcb9e8177ca18fa9fae756959d64d5ca1ca96d748d92d82f019", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4d2ee60a4a3deb2011971f56a0b98ecdebc89bb5be2290610c55114e3ee67f05", "generation_seconds_batch": 23.903164339018986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12965945899486542, "target_z": -0.22070312457087363, "ce": 5.0774359703063965, "genuineness": 4.193545341491699, "identity": 0.5484283566474915, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c3a9f8f19c28ffcb9e8177ca18fa9fae756959d64d5ca1ca96d748d92d82f019.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "c3bc92c95bbc5d25f1de9ea7231cc6fe3d7ebdc20dcc9e0dff37217655a9e29c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5fda10304fcaacb4c016d584a3490150e9c9e59e716c194b0eb11d57c46ddbaf", "generation_seconds_batch": 22.455489674932323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003068596124649048, "target_z": -0.5468750080103587, "ce": 6.046441555023193, "genuineness": 4.632867813110352, "identity": 0.6990349292755127, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c3bc92c95bbc5d25f1de9ea7231cc6fe3d7ebdc20dcc9e0dff37217655a9e29c.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "c3c4086b329eb21e61c8e7acec7acc05a23b03d0c61de6ea6c7318954a1310e4", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3da675f243c6bfdbb531a2c2a59d92c67dbef6b80dbb35832fe84cb8065438d1", "generation_seconds_batch": 24.524506040033884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1717827320098877, "target_z": -0.11718750171650544, "ce": 5.478540420532227, "genuineness": 4.494794845581055, "identity": 0.644437313079834, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c3c4086b329eb21e61c8e7acec7acc05a23b03d0c61de6ea6c7318954a1310e4.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "c3f51b2986cde10b9ded1613287535539449ca08316e38844496bb18389e5eca", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "30f6025da6bb4de905666565457957cab59c0390b043e9758aada7a4c297eaa9", "generation_seconds_batch": 22.701002361020073, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11137954890727997, "target_z": -0.2656249965669891, "ce": 6.1894097328186035, "genuineness": 4.758388519287109, "identity": 0.707856297492981, "hypothesis": "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_Bitterness/c3f51b2986cde10b9ded1613287535539449ca08316e38844496bb18389e5eca.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "c4096f9f97d6465e584cb320a1d13346f97bd13d5fd5a067fa256765f4ff31e2", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ca06d5f34956dc055bc396d87671e718a0e3680ec4d853a544e43e2c9a49c3e2", "generation_seconds_batch": 16.64944285596721, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09230485558509827, "target_z": -0.31250000457734783, "ce": 5.728734970092773, "genuineness": 4.7081804275512695, "identity": 0.5700826644897461, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c4096f9f97d6465e584cb320a1d13346f97bd13d5fd5a067fa256765f4ff31e2.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "7c9ea13cfea781970769ad63f96f9e177e58d663e8868488b41363569367d96e", "generation_seconds_batch": 17.4171530790627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08753618597984314, "target_z": -0.3242187474252418, "ce": 6.229123115539551, "genuineness": 4.262581825256348, "identity": 0.7579258680343628, "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_Bitterness/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "c576b282782c54aa7850c7f68862b0b3ea391d081511db309e0ff193bb64ae3a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "98a52ad49d69617aee64349a2eeafd1563b01574bae5e1cf6d6e60e08ab5687c", "generation_seconds_batch": 22.236621102900244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04382334649562836, "target_z": -0.4316406423080965, "ce": 5.3514580726623535, "genuineness": 4.482243061065674, "identity": 0.5663690567016602, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c576b282782c54aa7850c7f68862b0b3ea391d081511db309e0ff193bb64ae3a.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "c5949b9ad79665ae513fa44d3896645852749a3cea3295776278a621adcdf958", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "df9ecb2a7a8587c489f1bf3ff71b8c31fc341d903c6f4a866fbd95b49377ba9b", "generation_seconds_batch": 22.484359386959113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38637298345565796, "target_z": 0.41015621938898633, "ce": 5.808161735534668, "genuineness": 4.18099308013916, "identity": 0.04959474131464958, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c5949b9ad79665ae513fa44d3896645852749a3cea3295776278a621adcdf958.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "c5cc793e9b9723ef0863f09c55bdbb9f2ead543ad3e8613ecd0decabc8fa2a02", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "574c272166b5b08d0c475dc9045aaf4b7daa72dd1441f76df2fe50edfeeb8ff3", "generation_seconds_batch": 20.654469102970324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05415548384189606, "target_z": -0.4062499839792826, "ce": 6.141753673553467, "genuineness": 4.3504462242126465, "identity": 0.7368289232254028, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c5cc793e9b9723ef0863f09c55bdbb9f2ead543ad3e8613ecd0decabc8fa2a02.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "c5eb214e81ba6288763eafd6b7cd66dbba43ba9589bc6f5c7b70bb4dc4fb983b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1bd7b182cd61072724f77f9cedea1b38b2b69681e1cb7ce1e5f56855ddb17f30", "generation_seconds_batch": 23.551090560969897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17973051965236664, "target_z": -0.0976562514304212, "ce": 4.682784080505371, "genuineness": 4.21237325668335, "identity": 0.6128896474838257, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c5eb214e81ba6288763eafd6b7cd66dbba43ba9589bc6f5c7b70bb4dc4fb983b.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": "c63975ed504ef6de2844dad5fa1fe0d8592c0f30ea4c5ff0c2e220a84d6e0514", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f71a6d56f6c57d87f8929e26f0e87d52f01f901be071ffaba41d5d7df17cb65e", "generation_seconds_batch": 17.937284872983582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6963367462158203, "target_z": 1.1718750904026198, "ce": 6.284721851348877, "genuineness": 4.20609712600708, "identity": 0.6021761894226074, "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_Bitterness/c63975ed504ef6de2844dad5fa1fe0d8592c0f30ea4c5ff0c2e220a84d6e0514.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "c6a1b7b46ed3cc574c9f64f30a75a78e3548069cceb7981fcb8be32f341f843e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f7b586cd7fa7df0f4215711093bfceb4351bd2b4ab41d5b83dd711a18f0b6db2", "generation_seconds_batch": 17.126977498992346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16860361397266388, "target_z": -0.12500000915469567, "ce": 5.4388275146484375, "genuineness": 4.293961524963379, "identity": 0.6910407543182373, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c6a1b7b46ed3cc574c9f64f30a75a78e3548069cceb7981fcb8be32f341f843e.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "c6cb4ef357e7b0f1b096d86f65bb369e3e4526b108fd7f419bba2a6a0c158eea", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b77c72a154801218a43bb0c5c4b0f6afdc59eb83876491c263100bfc4af4ae9f", "generation_seconds_batch": 22.380768028087914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054950252175331116, "target_z": -0.404296884583822, "ce": 6.284721851348877, "genuineness": 4.300237655639648, "identity": 0.29501211643218994, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c6cb4ef357e7b0f1b096d86f65bb369e3e4526b108fd7f419bba2a6a0c158eea.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "c7af4193c0dd23d356f63ae1d122940272ed96a6122a2e89b360383f27a12125", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "089549bac2cda922236bb63555f3581a49641a55f7363e73bd5f38b7edd06094", "generation_seconds_batch": 22.050783179933205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17019318044185638, "target_z": -0.1210937371262092, "ce": 5.919358730316162, "genuineness": 4.3127899169921875, "identity": 0.511906087398529, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c7af4193c0dd23d356f63ae1d122940272ed96a6122a2e89b360383f27a12125.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "c7dfd64f1c0e98effc0699b1d2d53eb30b64005f30b12157589d6b474f6d076c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6e0afcd7ca758926cfa9649c6462d044d6d6b3066c31879734a0f5978304d241", "generation_seconds_batch": 24.23628716391977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02214328944683075, "target_z": -0.5937500160207174, "ce": 6.395919322967529, "genuineness": 4.607763767242432, "identity": 0.5156034827232361, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c7dfd64f1c0e98effc0699b1d2d53eb30b64005f30b12157589d6b474f6d076c.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "c7e0dfa28c30e7ed843c6044d06e228b44343069c64be1461754b446a473a6b5", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7ad218594324c403011ef048ae6f2e6892bf6f6c233c3b72d4f8367838c25e6b", "generation_seconds_batch": 20.622499261051416, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003068596124649048, "target_z": -0.5468750080103587, "ce": 6.292664527893066, "genuineness": 4.545003414154053, "identity": 0.4570070207118988, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c7e0dfa28c30e7ed843c6044d06e228b44343069c64be1461754b446a473a6b5.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "c7f6bb15c0cb6ae160dc10af5daf8a23e3daed6cf471c9553f8ce5dfc8c9238e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9defe02f20b75fb77dc297d0bd236e45b6d58e81f8976a56a45d1545f6e43ffd", "generation_seconds_batch": 14.849936492042616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09468919038772583, "target_z": -0.30664063315340084, "ce": 5.998785495758057, "genuineness": 4.325342178344727, "identity": 0.24756252765655518, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c7f6bb15c0cb6ae160dc10af5daf8a23e3daed6cf471c9553f8ce5dfc8c9238e.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "9afc87a88d7fae97dfd41eebdc3ca7a839b48c3f7f3c9a0945853573bf9b372f", "generation_seconds_batch": 17.027433671057224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0899205207824707, "target_z": -0.3183593760012948, "ce": 6.23706579208374, "genuineness": 4.293961524963379, "identity": 0.5755536556243896, "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_Bitterness/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "heldout-en-3", "language": "en", "sentences": [ "Someone moved the little blue chair.", "It used to stand here... beside the tall bookshelf.", "We can put it back after lunch." ], "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-3", "key": "c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "d5ca6384e19aad7062aad8f38884686d4de45642f9d96746d658b244f3c7cc1d", "generation_seconds_batch": 19.429479795042425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06766670942306519, "target_z": -0.3730468914498438, "ce": 6.4515180587768555, "genuineness": 4.419482707977295, "identity": 0.28622323274612427, "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_Bitterness/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "c93332f1a1d88986d5deb4faa6d304f7b50b7ac6f68ee7740c4705a1923aa96e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7dc13a1190d34dff06cd2aee45f5f7c09857b3fa4a16b2a632b72ebeeb9eea30", "generation_seconds_batch": 23.182705346029252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07164061069488525, "target_z": -0.3632812479974103, "ce": 5.808161735534668, "genuineness": 4.7834930419921875, "identity": 0.6155014038085938, "hypothesis": "Encontrado la cajita. Estaba junto la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.11764705882352941, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c93332f1a1d88986d5deb4faa6d304f7b50b7ac6f68ee7740c4705a1923aa96e.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": "c968814a144bd0261ee436fa375e9f0f9a8abb3e77f1f493d38c2e59176f67b6", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I wrote the number on the envelope.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0d2f2894f7b3b820898086f836a1e72d787be0a729140125557c104966807f76", "generation_seconds_batch": 23.50218565389514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0986630842089653, "target_z": -0.2968750080103587, "ce": 6.1894097328186035, "genuineness": 4.162164688110352, "identity": 0.2750144302845001, "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_Bitterness/c968814a144bd0261ee436fa375e9f0f9a8abb3e77f1f493d38c2e59176f67b6.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "c97a661834295615d6ad187dc9da04b4b4c40fd2417ede9ca0356fc43ce0d100", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "98b876a03fba9e2730fc543a5f2ee89a3a5a8248920760e473ee9797cca7d9a3", "generation_seconds_batch": 17.31518670299556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12012211233377457, "target_z": -0.244140628576053, "ce": 6.086154937744141, "genuineness": 4.3127899169921875, "identity": 0.5762666463851929, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/c97a661834295615d6ad187dc9da04b4b4c40fd2417ede9ca0356fc43ce0d100.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "ca35be8f3220d156089b8510afa994bdb37fe5cd128518d95f3231e3736be034", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ce529e2748290318e0d15b57f721391f3bc150942ecd9c56cb391fd6c62614ff", "generation_seconds_batch": 21.9847055550199, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09627874940633774, "target_z": -0.3027343794343057, "ce": 5.871703147888184, "genuineness": 4.482243061065674, "identity": 0.6050097942352295, "hypothesis": "La porte 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_Bitterness/ca35be8f3220d156089b8510afa994bdb37fe5cd128518d95f3231e3736be034.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "caa31b065badce15e290aaff6e1e8ed14f7a7016e2b91777d0f982718227e545", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4218a74d2718bc4e204c8d07bc5f82249aa94cda220f72290d0426592767b7db", "generation_seconds_batch": 17.324337125988677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13999158143997192, "target_z": -0.1953125028608424, "ce": 5.637393951416016, "genuineness": 4.607763767242432, "identity": 0.3116075098514557, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/caa31b065badce15e290aaff6e1e8ed14f7a7016e2b91777d0f982718227e545.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "caae3717bec02b8362390b1f313281c4a51ed66a04ae81120255362a14ba58fc", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b16edb83ce7fd018009478d2e8127e052d76c0edbff029fbae6d041b4e3e86f8", "generation_seconds_batch": 22.548143638996407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2115216702222824, "target_z": -0.01953125028608424, "ce": 5.7247633934021, "genuineness": 4.482243061065674, "identity": 0.7243711352348328, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/caae3717bec02b8362390b1f313281c4a51ed66a04ae81120255362a14ba58fc.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "cab81f12a214c4432529db85feece8f3809928b1646bc94c932ea7a3b75f8b60", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "02a96c5d53b4924546ac8c1c96b2fe8446f7b5548c07a983608ddaff3279a734", "generation_seconds_batch": 17.406483344035223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1455550342798233, "target_z": -0.18164062399870515, "ce": 5.704906940460205, "genuineness": 4.406930446624756, "identity": 0.5773783326148987, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/cab81f12a214c4432529db85feece8f3809928b1646bc94c932ea7a3b75f8b60.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": "cab8e3efcb4a322b472eb0864eb31d2b0454b14b16fba141bf6d61cc39e639e3", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd2b7fe9ac5f8196ebe0c9ea4ccf6768c24639a074545a91baf7ba096e5acd51", "generation_seconds_batch": 23.938470973982476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18767830729484558, "target_z": -0.07812500114433696, "ce": 5.673136234283447, "genuineness": 4.632867813110352, "identity": 0.7578557729721069, "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_Bitterness/cab8e3efcb4a322b472eb0864eb31d2b0454b14b16fba141bf6d61cc39e639e3.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "cb5057b1a8f3ae15ca448e4d4c323291fe5b526d425aa77b986f9f22c36f795e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ab602ff866fcd62405d33832a5252eaf4b7aea02157b400683e6cd6246257e42", "generation_seconds_batch": 31.832273195963353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.049386799335479736, "target_z": -0.4179687634459593, "ce": 5.6254801750183105, "genuineness": 4.093128204345703, "identity": 0.34601378440856934, "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_Bitterness/cb5057b1a8f3ae15ca448e4d4c323291fe5b526d425aa77b986f9f22c36f795e.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "cbea8b9b2a8601cfe6ce3d4d8701ababae65d66aee7ac15465ea026af940a286", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e98955d5b306d910a34201112e1e584c8e8f5a59223829a7ad0a620e4f689c50", "generation_seconds_batch": 15.949503679992631, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14873415231704712, "target_z": -0.17382811656051492, "ce": 6.260893821716309, "genuineness": 4.846253395080566, "identity": 0.7135578989982605, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/cbea8b9b2a8601cfe6ce3d4d8701ababae65d66aee7ac15465ea026af940a286.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "cc1d9bfae04643703a6c5b5f03a9f40406af8439a1008918bf4cce6aab6cc3f3", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1985394f52ed5af9966a98904c941aa88bdd3717c63bc16e8bfa7e0a310242bc", "generation_seconds_batch": 23.548228336963803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02373284101486206, "target_z": -0.5976562514304212, "ce": 6.348263263702393, "genuineness": 4.570107460021973, "identity": 0.22672605514526367, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/cc1d9bfae04643703a6c5b5f03a9f40406af8439a1008918bf4cce6aab6cc3f3.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "cc40d7d0e72a02a2a6e8e236f5ffc8cdd02e2679a47d5abb799cf6e38a42cfa1", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c2ac203be0e0654ba834b5f9e73a9203992a361d1004f1935fcdba9191e3f2e8", "generation_seconds_batch": 24.910094938008115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08833096921443939, "target_z": -0.3222656114109986, "ce": 5.855817794799805, "genuineness": 4.331617832183838, "identity": 0.7261896133422852, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/cc40d7d0e72a02a2a6e8e236f5ffc8cdd02e2679a47d5abb799cf6e38a42cfa1.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "cc47a18ff7667ccea04bbeef01109d2b98ca0143caea9682c579526bb2a39547", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3972a4cf70cec60904fbaa35d3c231a737dde7b2b486aba650b67dbefbf7a51a", "generation_seconds_batch": 24.913341960054822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09786830842494965, "target_z": -0.2988281257152106, "ce": 6.284721851348877, "genuineness": 4.645420074462891, "identity": 0.501451849937439, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/cc47a18ff7667ccea04bbeef01109d2b98ca0143caea9682c579526bb2a39547.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "cc50741987b5ef9c7ffcbfc7ac15cea9f63beebd84274c97e342d0315ab39231", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "63cad4a2f54ee055118b9480898371404d7995aa50681ef3fceb858f63e24572", "generation_seconds_batch": 16.96245014993474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003068596124649048, "target_z": -0.5468750080103587, "ce": 6.300607204437256, "genuineness": 4.381826400756836, "identity": 0.32189252972602844, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/cc50741987b5ef9c7ffcbfc7ac15cea9f63beebd84274c97e342d0315ab39231.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "cc863e30a5a3925331ec7fe6d85d4ef4d6be9fad273c186dcc0a259cc1c356e0", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bcddd84817ee02ea6bdf51d63f0b8355d5a10452549869c01c8efb8fadb158d1", "generation_seconds_batch": 16.114960588980466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.143965482711792, "target_z": -0.18554685940840893, "ce": 5.967014789581299, "genuineness": 4.6956281661987305, "identity": 0.7500604391098022, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/cc863e30a5a3925331ec7fe6d85d4ef4d6be9fad273c186dcc0a259cc1c356e0.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "cd3f06024c0f79e3e3613d95f7f2807747323f8ba774bde5255b7753f9cfb293", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1a23947970e76fd8d5ebe3da6056a9c3a3e092f28723cb2fd9cc2e9adcc98558", "generation_seconds_batch": 22.167185790953226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011237427592277527, "target_z": -0.511718742847894, "ce": 6.181467056274414, "genuineness": 3.8546390533447266, "identity": 0.1266089379787445, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/cd3f06024c0f79e3e3613d95f7f2807747323f8ba774bde5255b7753f9cfb293.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": "cd5787eb53c9884528639b28f730bc370e29245db1ef75cdbad5c7962033054a", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a2dfba91074f385f649ddb0e9b0a89e24c3768e6938d22b75c4a562eb036e7a9", "generation_seconds_batch": 16.331352062057704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22344335913658142, "target_z": 0.009765643452433482, "ce": 5.522225379943848, "genuineness": 4.306513786315918, "identity": 0.5280450582504272, "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_Bitterness/cd5787eb53c9884528639b28f730bc370e29245db1ef75cdbad5c7962033054a.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "cdbcb72bfd59226797d698bff242ad2a8e63022eda08ebd2dcc04ea838154dca", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ed66482b328efb12ebb0b69cb29338179082c0a1b6675e63991b17316c4909fc", "generation_seconds_batch": 23.153591564972885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14317069947719574, "target_z": -0.18749999542265217, "ce": 5.538110733032227, "genuineness": 4.545003414154053, "identity": 0.6512346863746643, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/cdbcb72bfd59226797d698bff242ad2a8e63022eda08ebd2dcc04ea838154dca.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "cdda03b8b76d158767dffc2bdf9191f2e5b687c41bce52f8220f495eacc78736", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d2f04ff7c9990fe1f81a7a480e99a2d3416676a05c543f8288e93063b0848db9", "generation_seconds_batch": 26.375579490093514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.060513705015182495, "target_z": -0.3906250057216848, "ce": 5.804190158843994, "genuineness": 4.093128204345703, "identity": 0.35877758264541626, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/cdda03b8b76d158767dffc2bdf9191f2e5b687c41bce52f8220f495eacc78736.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "cdeb40c48548a4f892c5913f7463179995f8b6752e730dd59e0e3b09f14987ef", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7ffd2076417d7e346cc89455907c00b0de297c957ceeb38a6f8939cf06707bba", "generation_seconds_batch": 22.57568104204256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01997998356819153, "target_z": -0.49023439316634926, "ce": 6.1894097328186035, "genuineness": 4.821148872375488, "identity": 0.6412365436553955, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/cdeb40c48548a4f892c5913f7463179995f8b6752e730dd59e0e3b09f14987ef.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "ce1ab8db8f70a1f058af1a5f2cfcb965dc22672abefffd2dd5785de678cde121", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "71f05acf2a46a6cdea16b6941593485e867c62992b43d53777c719098cf73ec1", "generation_seconds_batch": 23.099110975977965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08435706794261932, "target_z": -0.3320312548634321, "ce": 6.054384231567383, "genuineness": 4.7458367347717285, "identity": 0.7270705699920654, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/ce1ab8db8f70a1f058af1a5f2cfcb965dc22672abefffd2dd5785de678cde121.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "cede4ca42d9c5ed6f64956f2c311c0617b3a3eb68df2c3e925edc56978481229", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "66a842f677f4dfecfa2a1d73a4dbe50e583a8b47c826655f723beb39aad4b122", "generation_seconds_batch": 23.315498390002176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11376388370990753, "target_z": -0.25976562514304213, "ce": 6.046441555023193, "genuineness": 4.758388519287109, "identity": 0.6590489149093628, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/cede4ca42d9c5ed6f64956f2c311c0617b3a3eb68df2c3e925edc56978481229.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": "cf50436b4a9526b8336e46e390a45556ab35939b320258cfd2a4890eb896df0b", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a3625fd261a70e597375d53f1b522956062c0670c901305e1de50a0d44e8f538", "generation_seconds_batch": 18.12491953501012, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1995999813079834, "target_z": -0.04882814402460196, "ce": 6.09409761428833, "genuineness": 4.883909225463867, "identity": 0.7953213453292847, "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_Bitterness/cf50436b4a9526b8336e46e390a45556ab35939b320258cfd2a4890eb896df0b.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "da16f4f1f094dd7631c37483faf37207836e815a7a200aa3a578e36c684f929d", "generation_seconds_batch": 16.332335310056806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035875558853149414, "target_z": -0.4511718925941808, "ce": 6.38797664642334, "genuineness": 4.293961524963379, "identity": 0.5597460865974426, "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_Bitterness/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "cf90c8e2cb68c622f0ac5738057215ffc827f620d0b1434ed2416480eec4e037", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "dabd22f56860ea776c0f54060048cb076f4eb334a9a638e936648ccb05e849e9", "generation_seconds_batch": 23.471891490044072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09707353264093399, "target_z": -0.30078124342006246, "ce": 6.173524379730225, "genuineness": 4.3881025314331055, "identity": 0.730394721031189, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/cf90c8e2cb68c622f0ac5738057215ffc827f620d0b1434ed2416480eec4e037.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "cfc5b123942e0169d7a1d0df77df129d5fa0217e43094dbc6b54b3a7eab8c840", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "22072fe03f4dcdc1060a9e83fbd1997d56774ba4905cdddde059aa37ed44a6a7", "generation_seconds_batch": 22.7656983199995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1280699074268341, "target_z": -0.2246093599805774, "ce": 5.764476776123047, "genuineness": 4.419482707977295, "identity": 0.6618854999542236, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/cfc5b123942e0169d7a1d0df77df129d5fa0217e43094dbc6b54b3a7eab8c840.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "cfc7faaecb507ef6f48fcf7751aab2665b58f286a5db00b58f772b9211609e74", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ea3d68cf466ee452d240878cbc086d4a70282380bcf59cfda979918c37e94574", "generation_seconds_batch": 23.369413670967333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12171167135238647, "target_z": -0.24023437485695787, "ce": 5.180690288543701, "genuineness": 4.193545341491699, "identity": 0.5890421867370605, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/cfc7faaecb507ef6f48fcf7751aab2665b58f286a5db00b58f772b9211609e74.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "cfe9b5a362e7a7f539be68fee1df8407ab5b24691c38a84ab1d03b2d708adf6d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "238930e14945c161c5227bd2a18aba5b3b60af448ad3fd0323ff02e1eb8bdb9c", "generation_seconds_batch": 22.87148223305121, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05415548384189606, "target_z": -0.4062499839792826, "ce": 6.2767791748046875, "genuineness": 4.400654315948486, "identity": 0.7627847194671631, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/cfe9b5a362e7a7f539be68fee1df8407ab5b24691c38a84ab1d03b2d708adf6d.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "d01867ac5e855e48d4fcfaabb801181245ac58f16ac9e933e0de3490c783ff19", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1ee693752f63e5081fa66ceb196d64b700130d8c878fc89d968130e43087d351", "generation_seconds_batch": 15.08694672002457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17734618484973907, "target_z": -0.1035156228543682, "ce": 5.677107334136963, "genuineness": 4.6705241203308105, "identity": 0.5605904459953308, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d01867ac5e855e48d4fcfaabb801181245ac58f16ac9e933e0de3490c783ff19.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "d022a0ab9bef7f26b6216ddfabfd4edf7b2b8467993d63489d90017aa5f025f1", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9f4553a4bc9baf3bf93c7d9a02302238058702ac0f4281f6b44e0d880b340d50", "generation_seconds_batch": 22.12626471905969, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.015785053372383118, "target_z": -0.578125001144337, "ce": 6.157639026641846, "genuineness": 4.6956281661987305, "identity": 0.3927883505821228, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d022a0ab9bef7f26b6216ddfabfd4edf7b2b8467993d63489d90017aa5f025f1.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "d04ce5725f6b00443459d8463df8ed0ec0932eae364085297fa8e9d285aba441", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2259ab4bc404a3e23985bba91a64ac8a9f9a17951bb5f74c354b886e48c003a3", "generation_seconds_batch": 17.671411344897933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15986105799674988, "target_z": -0.14648435883624045, "ce": 5.534139156341553, "genuineness": 4.532451152801514, "identity": 0.7026194334030151, "hypothesis": "La porte 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_Bitterness/d04ce5725f6b00443459d8463df8ed0ec0932eae364085297fa8e9d285aba441.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "d059bda7f9d433471020c047932b994377c626875538cb31a67d27983d726dcf", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1d6f04f36716685c7476bf0558141692ab251d9a3fc60969f43943b5b854ec62", "generation_seconds_batch": 22.605092879966833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1717827320098877, "target_z": -0.11718750171650544, "ce": 5.411027908325195, "genuineness": 4.645420074462891, "identity": 0.3448724150657654, "hypothesis": "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_Bitterness/d059bda7f9d433471020c047932b994377c626875538cb31a67d27983d726dcf.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "fad1594e41a079a6f58ff680cae4c2af96dc14fd323f2fd4eda289be892a68e1", "generation_seconds_batch": 17.925391880911775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02792777121067047, "target_z": -0.470703142880265, "ce": 6.4515180587768555, "genuineness": 4.017816066741943, "identity": 0.3363827168941498, "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_Bitterness/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "d11cbe57277b6c48b798d15c8777d18db5a0a96eb17b714c93d8231d6d84f363", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a39b15ee95c8366b81c7f13077607da2b145048ba1bdf9255866c661ea897132", "generation_seconds_batch": 21.85766258800868, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11694300174713135, "target_z": -0.2519531177048519, "ce": 6.125868320465088, "genuineness": 4.356721878051758, "identity": 0.20457234978675842, "hypothesis": "The door still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d11cbe57277b6c48b798d15c8777d18db5a0a96eb17b714c93d8231d6d84f363.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "d171c436645c3939fd936323c41d0b456df4512e95ebc2148bb4a2b116681169", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d748955f6f56890b725331203185aed376622117a6f454d8ee645e8db4b3f4ad", "generation_seconds_batch": 22.87373704498168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13204379379749298, "target_z": -0.21484375314692664, "ce": 5.9431867599487305, "genuineness": 4.833701133728027, "identity": 0.4298275113105774, "hypothesis": "La porte 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_Bitterness/d171c436645c3939fd936323c41d0b456df4512e95ebc2148bb4a2b116681169.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "5893f2f1ab8865deb80dd2074f0d22ba3299678ee6ea3178dd6973d56fea5d44", "generation_seconds_batch": 17.536666880943812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01997998356819153, "target_z": -0.49023439316634926, "ce": 6.332377910614014, "genuineness": 4.268857479095459, "identity": 0.5211999416351318, "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_Bitterness/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "d26acc4e47a919c791ade2bf8ec61fd6a96fcff9b3328705dc98a53d1e3494c0", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "87c4ec82439bd52094c35293d880ce6324d89d66e102dd0c58b59966df6a53d2", "generation_seconds_batch": 15.97256846295204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07005105912685394, "target_z": -0.3671874834071141, "ce": 6.1894097328186035, "genuineness": 4.720732688903809, "identity": 0.716161847114563, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d26acc4e47a919c791ade2bf8ec61fd6a96fcff9b3328705dc98a53d1e3494c0.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "d2d29f5cdd282fa4242fdf84c53abcdbe305470c29f37952196d5dd48caaa250", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "72b35ba0ff79d76f2591c996236d7d310a56c6d4c79359525febfca58471fd51", "generation_seconds_batch": 18.082657355000265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12965945899486542, "target_z": -0.22070312457087363, "ce": 5.287916660308838, "genuineness": 4.3127899169921875, "identity": 0.4960511326789856, "hypothesis": "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_Bitterness/d2d29f5cdd282fa4242fdf84c53abcdbe305470c29f37952196d5dd48caaa250.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "d2e1f9e0bf488cd58a507a2968fa9dcd9d6ce4f5df478e17d7bc63423bdd1b78", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a0c1096e7d6d9bf8e9ab8891186022c4a6ec7db9a361527e3e6f38cfd368b3a7", "generation_seconds_batch": 23.302713002078235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12409600615501404, "target_z": -0.23437500343301088, "ce": 5.919358730316162, "genuineness": 4.256305694580078, "identity": 0.43185603618621826, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d2e1f9e0bf488cd58a507a2968fa9dcd9d6ce4f5df478e17d7bc63423bdd1b78.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "d333f453485deaf3552d4dc388d2bbc5fb303906f7da0ed62bd73508d09020c0", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9de00b3064e851de722137f1f954f7b0a19810a74fdc1d7529ecc4b6af034d41", "generation_seconds_batch": 27.36135235801339, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03349122405052185, "target_z": -0.45703126401812777, "ce": 6.348263263702393, "genuineness": 4.469690799713135, "identity": 0.49842730164527893, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d333f453485deaf3552d4dc388d2bbc5fb303906f7da0ed62bd73508d09020c0.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "d33714b5aec39b99b35ada03a36f8c9cadcb77560f8e889caa2560a01c4496e1", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9b7399de851f09db7b72e1b752e17b71fc4786346bb5475a71b8f1c5218b4b37", "generation_seconds_batch": 24.09104685706552, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12727512419223785, "target_z": -0.22656249599482065, "ce": 6.308549880981445, "genuineness": 4.557555198669434, "identity": 0.2675350606441498, "hypothesis": "The door's still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d33714b5aec39b99b35ada03a36f8c9cadcb77560f8e889caa2560a01c4496e1.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": "d3983099c565f2f7b5c7da35f0bf17d0f4ab77f615ef36f08b3743899c17c0a2", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ddd8cfcb8fb4e6153d5cf0da11605dd859193bdd4ba8c2094068ccf7758d8a41", "generation_seconds_batch": 18.12491953501012, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24410760402679443, "target_z": 0.06054688687249596, "ce": 5.895530700683594, "genuineness": 4.632867813110352, "identity": 0.7484551072120667, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi qu'on ne pourront parler.", "wer": 0.14285714285714285, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d3983099c565f2f7b5c7da35f0bf17d0f4ab77f615ef36f08b3743899c17c0a2.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "d3f39f30771fe596e99e9d3efe47eb395fccc37f871dba092c904b9528b88101", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d4a7d3b6634dd5991a033f469cf25591d50a075134f7e4d73a9df72094c887f5", "generation_seconds_batch": 28.313874340965413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.117737777531147, "target_z": -0.25, "ce": 6.070269584655762, "genuineness": 4.545003414154053, "identity": 0.6378501653671265, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d3f39f30771fe596e99e9d3efe47eb395fccc37f871dba092c904b9528b88101.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "d3f7e87572619f7e7f99259e222bf076c9849034052dc2c5417fe66e9d8d96fb", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a4d97f3d3e570dc706e7362fd3df63ff2ad8f9e9f451941324edd87c98171ffe", "generation_seconds_batch": 17.126977498992346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07720406353473663, "target_z": -0.3496093691352731, "ce": 5.689021587371826, "genuineness": 4.13078498840332, "identity": 0.5680848360061646, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d3f7e87572619f7e7f99259e222bf076c9849034052dc2c5417fe66e9d8d96fb.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "95f48e1e2d520744652cb5c9819c575ca545591e9e5cd69915ca5cf203bfd103", "generation_seconds_batch": 17.207908757962286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003289639949798584, "target_z": -0.5312499931339782, "ce": 6.0146708488464355, "genuineness": 4.381826400756836, "identity": 0.611572802066803, "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_Bitterness/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "d49e85d93cc34c8d3175d9561273f584e2f2e53e28e088c14ca4f90ba97cfb64", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f9973f313ad9ae5a6ba01ca3d13992504725529a1dd6e0fcd7eba479c2794d79", "generation_seconds_batch": 22.57568104204256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10502132028341293, "target_z": -0.28124999313397825, "ce": 5.7684478759765625, "genuineness": 4.871357440948486, "identity": 0.7164212465286255, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d49e85d93cc34c8d3175d9561273f584e2f2e53e28e088c14ca4f90ba97cfb64.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": "d5cb7827c61ece5ae6892223c1aba6d69759366bbce7f1f9ab09d12b4b2240bf", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e97cf1a98aad3174585a70ef5b84d3575304da9e068ec0d78ddd00df56d70b64", "generation_seconds_batch": 22.675173102063127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08912573754787445, "target_z": -0.32031251201553806, "ce": 5.9431867599487305, "genuineness": 4.6203155517578125, "identity": 0.5744731426239014, "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_Bitterness/d5cb7827c61ece5ae6892223c1aba6d69759366bbce7f1f9ab09d12b4b2240bf.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "d6543f1070a391c53dde79767fecb556ed951de2d1f5e6d656e05ba269ee2de0", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "35e2f3cc7ce26d36d65503727df1e32356f739246b6e0b6d01b6af57b825a5ba", "generation_seconds_batch": 22.306231147027574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21390600502490997, "target_z": -0.01367187886213724, "ce": 5.001980304718018, "genuineness": 4.149612903594971, "identity": 0.4679987132549286, "hypothesis": "Mm. La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d6543f1070a391c53dde79767fecb556ed951de2d1f5e6d656e05ba269ee2de0.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "d6a4c90b1261c311f1c2fb0a48dd2e7ebf0b36948000b5dc0ff9956227c2a820", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d6300dbd8ab6246085d42209c191f8701b96c185d52b213e80c0a254a929613e", "generation_seconds_batch": 17.661625984008424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1837044060230255, "target_z": -0.08789064459677044, "ce": 6.0146708488464355, "genuineness": 4.758388519287109, "identity": 0.6945499181747437, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d6a4c90b1261c311f1c2fb0a48dd2e7ebf0b36948000b5dc0ff9956227c2a820.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "d7063c8101482c25bfac83b116e4e8974ffc90212b3d9439afc30833c1a19e81", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c8f88b46e63cc4b1ee8f39beb83e6749d0efb38e4a95e35373ab3eeb65ea512c", "generation_seconds_batch": 22.959730934002437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12250644713640213, "target_z": -0.238281257152106, "ce": 6.260893821716309, "genuineness": 4.344170093536377, "identity": 0.2727765738964081, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d7063c8101482c25bfac83b116e4e8974ffc90212b3d9439afc30833c1a19e81.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "d79925c3d605873419febd96b8b3011cd75e817f52375ae23fdf1772437be55b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c272a54f14c7a0628d92d091c00c6edfe8abb63f9aaf0617a9249f637e6d7372", "generation_seconds_batch": 23.321505650063045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12965945899486542, "target_z": -0.22070312457087363, "ce": 6.165581703186035, "genuineness": 4.105680465698242, "identity": 0.2892352342605591, "hypothesis": "The door is s still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d79925c3d605873419febd96b8b3011cd75e817f52375ae23fdf1772437be55b.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "d7cd20d7b778bc30a8496a80e7086fd74d871d8a359e8ad245bcf6784ddaf682", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4f7bc4c15dd070e3d16dc44226d616f62b9e9f798b3d5466ccc24abc67f05fd8", "generation_seconds_batch": 16.541487789014354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1542975902557373, "target_z": -0.1601562743171604, "ce": 6.149696350097656, "genuineness": 4.331617832183838, "identity": 0.7130880951881409, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d7cd20d7b778bc30a8496a80e7086fd74d871d8a359e8ad245bcf6784ddaf682.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "d7ea1411e372926510c4c1df1a220706cb8a94d5020d75bf803d9e1e52629089", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3fb239c8f67b729190c19395d495c287ee888c5735191191788095ccbae4297e", "generation_seconds_batch": 15.97256846295204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08356228470802307, "target_z": -0.33398439087767534, "ce": 6.24500846862793, "genuineness": 4.6705241203308105, "identity": 0.7416905760765076, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d7ea1411e372926510c4c1df1a220706cb8a94d5020d75bf803d9e1e52629089.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": "d7eb7e50dd097dddd9d3a29dfdc459e5e1bbb9fa9afde59288713095a6cd843e", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The road turns left behind the bridge.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "04c28bd6858c6e62841fef00da425f8613f4713e50692e29df99db5fad65767e", "generation_seconds_batch": 20.513461622060277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12409600615501404, "target_z": -0.23437500343301088, "ce": 6.38003396987915, "genuineness": 4.3504462242126465, "identity": 0.25785431265830994, "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_Bitterness/d7eb7e50dd097dddd9d3a29dfdc459e5e1bbb9fa9afde59288713095a6cd843e.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "d7ee857ac4eb22a5098de255d9d96371cf6710658a5fd5ee7576b89c34ecce3b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7d01573c9e13d1fcf01cff5704463c01b10e5d34f0b8b4a1ecb986ade2379032", "generation_seconds_batch": 25.347725435975008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.049386799335479736, "target_z": -0.4179687634459593, "ce": 6.41180419921875, "genuineness": 4.996878147125244, "identity": 0.6714454889297485, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d7ee857ac4eb22a5098de255d9d96371cf6710658a5fd5ee7576b89c34ecce3b.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "d80525410e394cbfff8d5dededef5c8d492d47d604e78a73e72c5b687235642d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5c0ba6fc3b43f3d3a0f37fe56e3a033323bea5a17dd4e69b34be5485b289414a", "generation_seconds_batch": 21.182747012004256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12409600615501404, "target_z": -0.23437500343301088, "ce": 6.2767791748046875, "genuineness": 4.469690799713135, "identity": 0.31578531861305237, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d80525410e394cbfff8d5dededef5c8d492d47d604e78a73e72c5b687235642d.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "d8663fe99a806260011c36f18bc1313c512342e0b3086430f303a121c8a60d79", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4c16058668116d1b6f296b9dab66e2cca78249af77392a704da77abb2f2d1dee", "generation_seconds_batch": 15.730160707957111, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12568557262420654, "target_z": -0.2304687314045244, "ce": 5.871703147888184, "genuineness": 4.425758361816406, "identity": 0.44438862800598145, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d8663fe99a806260011c36f18bc1313c512342e0b3086430f303a121c8a60d79.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "d869a32252daf27049290a3119560355d0a9788cc0c86b7d59d345639e46718d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a2f326807a43a17966ee401f4d4aa7b7fab35830ef0a9cdacd10340b6dfc89e4", "generation_seconds_batch": 26.978992001037113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21549555659294128, "target_z": -0.009765643452433482, "ce": 5.4944257736206055, "genuineness": 4.306513786315918, "identity": 0.1470145434141159, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d869a32252daf27049290a3119560355d0a9788cc0c86b7d59d345639e46718d.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "d8790dc12f9787b24565ddfc85a0aee252fe86685194837d7ae1a45b12119e2c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ebabb6159419e3137ef240dc5ab0010e75adfd565f1c8f4e77ce8ba19a06bc64", "generation_seconds_batch": 26.005073564010672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23139113187789917, "target_z": 0.029296857119735, "ce": 5.919358730316162, "genuineness": 4.18726921081543, "identity": 0.4748709797859192, "hypothesis": "Ik heb een klein doosje gevonden. Het stond naast het oude raam. We kunnen samen heen kijken.", "wer": 0.2222222222222222, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d8790dc12f9787b24565ddfc85a0aee252fe86685194837d7ae1a45b12119e2c.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "d8812c1633f53eb760224e16c09070d968e5895efc37d4fc3299924fe3611516", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "eb07e4bdf77f4a8a8e92cc679b522229f884b716726f80006fda57a8045efae7", "generation_seconds_batch": 18.343920178012922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16542449593544006, "target_z": -0.13281251659288593, "ce": 4.7875285148620605, "genuineness": 3.9676074981689453, "identity": 0.4501368999481201, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás.", "wer": 0.06666666666666667, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d8812c1633f53eb760224e16c09070d968e5895efc37d4fc3299924fe3611516.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "d8e32b63c259a6bb8b7e741e83b7b70b78ffcfcbbffc8dbc7d3087f8472c3d04", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "655e6a7afb0cfd9c1a6c4889207e2829b039a41b9dddf9c3da8ed885390e3f01", "generation_seconds_batch": 22.663737167953514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1821148544549942, "target_z": -0.09179688000647421, "ce": 6.125868320465088, "genuineness": 4.808597087860107, "identity": 0.7436480522155762, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d8e32b63c259a6bb8b7e741e83b7b70b78ffcfcbbffc8dbc7d3087f8472c3d04.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "d93405739ed1cc2203b2adf834f2ab58f2bbef8f94ed0a2048eb6b0a5101413d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "f4bd83e74d11169bb9a7cc7b7a98a92441c6e80d1f914ccdcbd872ed8a1389c7", "generation_seconds_batch": 22.16110268200282, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003068596124649048, "target_z": -0.5468750080103587, "ce": 6.221180438995361, "genuineness": 4.632867813110352, "identity": 0.7569911479949951, "hypothesis": "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_Bitterness/d93405739ed1cc2203b2adf834f2ab58f2bbef8f94ed0a2048eb6b0a5101413d.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "d93e6d9061522a492396ca8d265d012ce408f0184daea096a3ccd4a2f0c8cce7", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8249c8ba9fb45c5c95180b5663c74dba917a21d8681259400586339a50952e38", "generation_seconds_batch": 21.46593455807306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035080790519714355, "target_z": -0.4531249919896413, "ce": 6.340320587158203, "genuineness": 4.432034492492676, "identity": 0.6146001219749451, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d93e6d9061522a492396ca8d265d012ce408f0184daea096a3ccd4a2f0c8cce7.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "d9881e13d21f902ef4a4f0959c1529209dae8cb376b0930031bcc99f7b7fb24d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d536d3701aa90ac3fe70b4db985eb76ac46661118ef3b9522f7dba4ca7a46956", "generation_seconds_batch": 22.697491565020755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15509238839149475, "target_z": -0.15820310168413443, "ce": 5.895530700683594, "genuineness": 4.7332844734191895, "identity": 0.7131996154785156, "hypothesis": "La porte 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_Bitterness/d9881e13d21f902ef4a4f0959c1529209dae8cb376b0930031bcc99f7b7fb24d.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "d991e072d13ae8c127cffedb128924351402af8486e4569e03b3bf1704afeac3", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "afad4d8069a83ba4cb1f4519cce023c48c68207e9520742d6bf2a3daffa2c7bc", "generation_seconds_batch": 23.134968134923838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13601768016815186, "target_z": -0.2050781463132759, "ce": 6.205295085906982, "genuineness": 4.8588056564331055, "identity": 0.8156579732894897, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d991e072d13ae8c127cffedb128924351402af8486e4569e03b3bf1704afeac3.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "d998a9788b22a518ad5228ab850f5823fe9429e4f1152b87c61600d2f8c1462f", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "78d4c43d915b7dda9f6047171c270b9e60a98a21756ca33686f4d99c42ecce27", "generation_seconds_batch": 17.219643565942533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09389442205429077, "target_z": -0.30859373254886135, "ce": 6.173524379730225, "genuineness": 4.65797233581543, "identity": 0.780433177947998, "hypothesis": "La porte 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_Bitterness/d998a9788b22a518ad5228ab850f5823fe9429e4f1152b87c61600d2f8c1462f.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "d9b45eeef8dcbff323bdd1ae9be3f06c5397c4cbaf03618fe6cdebb6570dd478", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5478746fa5d600339732ee8abddab81858c1c25cd55e97f38f747c662c830a54", "generation_seconds_batch": 24.235803941031918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11694300174713135, "target_z": -0.2519531177048519, "ce": 6.046441555023193, "genuineness": 4.645420074462891, "identity": 0.6992509365081787, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/d9b45eeef8dcbff323bdd1ae9be3f06c5397c4cbaf03618fe6cdebb6570dd478.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "da113fcee9e67f037d01d38ee3e232256b1efc41a879d0dcbaf2da4b9af013cd", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b8de6291e8296c76af71b2af5fe6c54705c0de6c35cd67d69632c5bc839834d8", "generation_seconds_batch": 15.730160707957111, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12171167135238647, "target_z": -0.24023437485695787, "ce": 5.895530700683594, "genuineness": 4.413206577301025, "identity": 0.7102184295654297, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/da113fcee9e67f037d01d38ee3e232256b1efc41a879d0dcbaf2da4b9af013cd.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "da4ed64ff0f43f4d02a941e9d32535f7400de6d1f6b2d05815832f620f33a13f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c8b393e2385520d5b111114dba5131c4c336eaf72dc90fe030d45b265c4a2c20", "generation_seconds_batch": 25.315636298037134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17893573641777039, "target_z": -0.09960938744466444, "ce": 5.919358730316162, "genuineness": 4.7458367347717285, "identity": 0.6184425354003906, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/da4ed64ff0f43f4d02a941e9d32535f7400de6d1f6b2d05815832f620f33a13f.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": "dac8deec030c83aa72ee5beddf4d2919911b218b6beb6abf1e19c4534e1720cc", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The keys are on the kitchen table.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "493ce63e93f684c78001baf1aa0853f4dddc0224a8cba4fef9a2b0ea591bbde3", "generation_seconds_batch": 18.448489908943884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03905467689037323, "target_z": -0.44335938515599055, "ce": 6.284721851348877, "genuineness": 4.281409740447998, "identity": 0.3830479383468628, "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_Bitterness/dac8deec030c83aa72ee5beddf4d2919911b218b6beb6abf1e19c4534e1720cc.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "8f175078db2178c273fa6369482620d92db4250960ca3da08722d410181847ad", "generation_seconds_batch": 15.58396407798864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10025264322757721, "target_z": -0.2929687542912636, "ce": 6.41180419921875, "genuineness": 4.143336772918701, "identity": -0.01818622648715973, "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_Bitterness/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "db1d992c968154a5552ff9be4ee897427d93347942fc619f5be78930e0932d5c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8ce90da4061657ed47b61ab32bd6464abafb8a5ae58286a5e567e8f95dafa9de", "generation_seconds_batch": 23.60560069407802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07640928030014038, "target_z": -0.3515625051495163, "ce": 5.6413655281066895, "genuineness": 4.469690799713135, "identity": 0.1385507732629776, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/db1d992c968154a5552ff9be4ee897427d93347942fc619f5be78930e0932d5c.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "db4b8a5ae66db3edff89ee001c69f812adce9c63fcf9e84bfa42e0a0f627222c", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2feee01f36f77420a985b68832244dc04f250d9906abc60db651e6056495752b", "generation_seconds_batch": 18.405122285941616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05097636580467224, "target_z": -0.4140624914174728, "ce": 6.252951145172119, "genuineness": 4.432034492492676, "identity": 0.3066534101963043, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/db4b8a5ae66db3edff89ee001c69f812adce9c63fcf9e84bfa42e0a0f627222c.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": "db5a6d381fb9f9721d0a98bd00d19f31537990a1db03d9c1338e8828f46a8fcd", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5775925a871b905af752e4044cb873aae849c567d926b45edd72a0ea69a7016f", "generation_seconds_batch": 16.566019571968354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24172326922416687, "target_z": 0.05468751544854896, "ce": 5.816103935241699, "genuineness": 4.7081804275512695, "identity": 0.7275871634483337, "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_Bitterness/db5a6d381fb9f9721d0a98bd00d19f31537990a1db03d9c1338e8828f46a8fcd.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "db6ee8aa59be9e5c445beb73933429760feadd1daedcc0543ed64c1d5479d5bb", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9b56ba14ef23946ccd9e48f83380f8496884ce5ebdba8d3beb13df3c08662f45", "generation_seconds_batch": 23.000613381969742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04859203100204468, "target_z": -0.4199218628414198, "ce": 6.229123115539551, "genuineness": 4.281409740447998, "identity": 0.2966461479663849, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/db6ee8aa59be9e5c445beb73933429760feadd1daedcc0543ed64c1d5479d5bb.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "dba2ded4e753ef9264d702d3f5d81bd1acca3642f60096f27fff64f2258b416b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e48bb9714f35f1576ed18d6655d2868227a8bd8dd6e587b59034ffa3c653343c", "generation_seconds_batch": 23.302713002078235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11376388370990753, "target_z": -0.25976562514304213, "ce": 6.086154937744141, "genuineness": 4.557555198669434, "identity": 0.4104781150817871, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/dba2ded4e753ef9264d702d3f5d81bd1acca3642f60096f27fff64f2258b416b.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "dbb16ad3052832687557ecef7232fbf35f37afb3bf882097f83b595ee891eca5", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "95cd9f749d95a2a447d012e80e825929bd3f78c4b34c9236ea54f91ed89dbbaa", "generation_seconds_batch": 22.25143444503192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13601768016815186, "target_z": -0.2050781463132759, "ce": 5.7684478759765625, "genuineness": 4.570107460021973, "identity": 0.6896927356719971, "hypothesis": "La porte 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_Bitterness/dbb16ad3052832687557ecef7232fbf35f37afb3bf882097f83b595ee891eca5.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "dbf40c2a1d1e8c6c3fa9d385caba7df1830f8765469659460903ec8e6e9d1db7", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "815bdd3c82149424391bbdff31dd2491b3767c17d8b6ff86552df68eaf522e8d", "generation_seconds_batch": 21.592318866983987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.058924153447151184, "target_z": -0.39453124113138854, "ce": 5.696964263916016, "genuineness": 4.494794845581055, "identity": 0.7227879762649536, "hypothesis": "La porte 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_Bitterness/dbf40c2a1d1e8c6c3fa9d385caba7df1830f8765469659460903ec8e6e9d1db7.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "dcd3e247ee1d45993cb69e1b2d11f7ec612b383163e25acd726d4673141fea76", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "14154bc0f06f57e43712ae4853f2d1cb73ae29042765d7eab6ea839c3a8ca705", "generation_seconds_batch": 23.44817475392483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12250644713640213, "target_z": -0.238281257152106, "ce": 5.470598220825195, "genuineness": 4.595211505889893, "identity": 0.3634707033634186, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/dcd3e247ee1d45993cb69e1b2d11f7ec612b383163e25acd726d4673141fea76.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "dd14041f049ed623fe976293376b9603bd320b4ab3e6002568b83765e51c9070", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c07782280516af014cf3f982d66efcd881923f6df7af77146c68ad7668e6e1df", "generation_seconds_batch": 22.60861139104236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13045424222946167, "target_z": -0.2187499885566304, "ce": 5.927301406860352, "genuineness": 4.65797233581543, "identity": 0.7425892353057861, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/dd14041f049ed623fe976293376b9603bd320b4ab3e6002568b83765e51c9070.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": "dd1712009d0d672e210842e74bebb42e8555da24346c9f5fbb1f63cd4bec1190", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4b2bc88ca45da5d26795cf8abd8b73041ce02b08104f5702aa1777c49bc307b0", "generation_seconds_batch": 15.825979516957887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09230485558509827, "target_z": -0.31250000457734783, "ce": 5.7128496170043945, "genuineness": 4.595211505889893, "identity": 0.8635469675064087, "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_Bitterness/dd1712009d0d672e210842e74bebb42e8555da24346c9f5fbb1f63cd4bec1190.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "dd6871da261d533cd7d66b3e6ffe83c2f18839bdc1bde1a7b2d23acdfb83c83a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "30d1487765564faa951f5f7e7450e1de45231c483191aec1149bdf4c0c20c571", "generation_seconds_batch": 23.83910462493077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08912573754787445, "target_z": -0.32031251201553806, "ce": 6.332377910614014, "genuineness": 4.482243061065674, "identity": 0.1567847728729248, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/dd6871da261d533cd7d66b3e6ffe83c2f18839bdc1bde1a7b2d23acdfb83c83a.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "de579217d6de4a9a4a9df73b1d2c55e50eaaf7105e307e5ef302498b616142db", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "09239b5e1705891d243554e05d218ce50166426fc67ad97918e6747299505c62", "generation_seconds_batch": 23.482123175053857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12091689556837082, "target_z": -0.24218749256180977, "ce": 5.736677646636963, "genuineness": 4.7081804275512695, "identity": 0.6569373607635498, "hypothesis": "La porte 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_Bitterness/de579217d6de4a9a4a9df73b1d2c55e50eaaf7105e307e5ef302498b616142db.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "de6cae5f184896b8b3795b415e9a8ba6c3f022cb99a14577d04e20b1bc6d693b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d2502e59f858fcc29b76022f8768a636db98df6ddf46c80b1bd99525a6e0342c", "generation_seconds_batch": 20.884542836924084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24728670716285706, "target_z": 0.06835935769190347, "ce": 6.0305562019348145, "genuineness": 4.494794845581055, "identity": 0.3405144214630127, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/de6cae5f184896b8b3795b415e9a8ba6c3f022cb99a14577d04e20b1bc6d693b.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "deafde71275055877a764cfb9771e13e55530ad812609d0855d042491cc28a59", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "78eeebb51f714321dc0b7b97825994c0d9e21dc756d063d700e04ce4225d730d", "generation_seconds_batch": 16.981136107002385, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0899205207824707, "target_z": -0.3183593760012948, "ce": 6.173524379730225, "genuineness": 4.532451152801514, "identity": 0.6993645429611206, "hypothesis": "La porte 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_Bitterness/deafde71275055877a764cfb9771e13e55530ad812609d0855d042491cc28a59.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "df1af86a76cf7e29fec690f9c4bca1b08425415b33b627c97c95630d153942b4", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6b39c049c4c4426fce172b2e19c6e5fa59325545bb48c64f4fee8da5d20eb5a1", "generation_seconds_batch": 22.884328222018667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16621927917003632, "target_z": -0.1308593805786427, "ce": 5.327630043029785, "genuineness": 4.645420074462891, "identity": 0.5356595516204834, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/df1af86a76cf7e29fec690f9c4bca1b08425415b33b627c97c95630d153942b4.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "dfb1066dd93e543e8bbe4e9fc2daa92a00b2699d24b429825de6832144dea743", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5d71dfce1456795216c0c2283ccd8032a01849bb410f810d18ca3a4718b503a6", "generation_seconds_batch": 17.78396177093964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13999158143997192, "target_z": -0.1953125028608424, "ce": 5.6532793045043945, "genuineness": 4.833701133728027, "identity": 0.7058560848236084, "hypothesis": "La porte 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_Bitterness/dfb1066dd93e543e8bbe4e9fc2daa92a00b2699d24b429825de6832144dea743.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "e05a6214e7c21f8e14ed94d02fb23ef45910d0b252c07d9d1443e9416fad8585", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "53aacc770c10bf3c55b078e25cb3b02f5d5cc53cb39bfba9d6efb82e8a343f22", "generation_seconds_batch": 17.406483344035223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2011895477771759, "target_z": -0.04492187199611548, "ce": 5.696964263916016, "genuineness": 4.482243061065674, "identity": 0.6928912401199341, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/e05a6214e7c21f8e14ed94d02fb23ef45910d0b252c07d9d1443e9416fad8585.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "e095a67a7e5adb89aafd6def1d3347da8b462729ddfc0e83153f367fdfa6ec64", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0eff0d092571e8b5717948021d0788cb4192f87e55fb0b3ff95055e1e965a460", "generation_seconds_batch": 24.42755339795258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016800880432128906, "target_z": -0.49804686398575676, "ce": 6.1894097328186035, "genuineness": 4.758388519287109, "identity": 0.7576984167098999, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/e095a67a7e5adb89aafd6def1d3347da8b462729ddfc0e83153f367fdfa6ec64.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "e18ac47e12b14663387e32f8b56cc7d02789c7a2811b54768108697e3c161208", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5e886810e0a7846baacd0f8f26c555e60a82adf3845e6c25894d185d2535d818", "generation_seconds_batch": 25.01043241401203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027133002877235413, "target_z": -0.4726562422757255, "ce": 6.372091293334961, "genuineness": 4.6203155517578125, "identity": 0.5021129846572876, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/e18ac47e12b14663387e32f8b56cc7d02789c7a2811b54768108697e3c161208.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "e19355566522b1ac652fa47a81922bc14a256231fa1f22535abd7e37a4d91e64", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6bdb07590f16e7983ec7d28d7765664de74369addc3f83f929aafd10376cfb3f", "generation_seconds_batch": 22.53937918401789, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15827149152755737, "target_z": -0.15039063086472693, "ce": 5.736677646636963, "genuineness": 4.68307638168335, "identity": 0.5090789794921875, "hypothesis": "Ik heb het een kleine doosje gevonden. Het stond naast het oude ramen. We kunnen er samen in kijken.", "wer": 0.1111111111111111, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/e19355566522b1ac652fa47a81922bc14a256231fa1f22535abd7e37a4d91e64.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "e23e910f877c89df61eb217b49feb8141b5a52b39157f64bc874098162e724a8", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "340e948792c40c3f314fc44f0689eee9d8864cf09c9903ec92b3a5b891606148", "generation_seconds_batch": 21.355889252969064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11376388370990753, "target_z": -0.25976562514304213, "ce": 6.078212261199951, "genuineness": 4.68307638168335, "identity": 0.8070048093795776, "hypothesis": "La porte 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_Bitterness/e23e910f877c89df61eb217b49feb8141b5a52b39157f64bc874098162e724a8.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "e298ed0fec214c82421fdcd4c0f8f7b5605f55576b58d39a68cbb89a87b7d065", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c3257a09e90c49220dd0c4093925726e1079cd38c355ba232d7c2331f35542fe", "generation_seconds_batch": 23.22800625709351, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10343176126480103, "target_z": -0.28515624685307334, "ce": 6.157639026641846, "genuineness": 4.369274139404297, "identity": 0.6399461030960083, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/e298ed0fec214c82421fdcd4c0f8f7b5605f55576b58d39a68cbb89a87b7d065.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "e30b6d3d6ccaa0ba57035adf4e44828ef8a94b2166815f7321b806d727d885d0", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "84343960ef6375bc0fb3ffcb6fdedcd953044770f73d3af4cbf71ba9e364fb07", "generation_seconds_batch": 24.047341816942208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22423812747001648, "target_z": 0.011718742847893999, "ce": 5.998785495758057, "genuineness": 4.469690799713135, "identity": 0.5254212617874146, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/e30b6d3d6ccaa0ba57035adf4e44828ef8a94b2166815f7321b806d727d885d0.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "e35bd84690d43a3416968206b97f324e1cc779814a71e26c0d084ca44b6b5345", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "db4b2658b9bb101c7f11b404b25803439f4a27d8e7c7f638f113de8b0b6c253a", "generation_seconds_batch": 22.811391772003844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16224539279937744, "target_z": -0.14062498741229343, "ce": 6.300607204437256, "genuineness": 4.532451152801514, "identity": 0.5517091155052185, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/e35bd84690d43a3416968206b97f324e1cc779814a71e26c0d084ca44b6b5345.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "e35e039d5a23d83a3befb63dde6282d20f748d572a6cda645a3aa58d0b365c23", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d65dfa982fd2052411044e1825dd1045ef4542041a644c911e6f64b43b9bd3bc", "generation_seconds_batch": 16.541487789014354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16542449593544006, "target_z": -0.13281251659288593, "ce": 6.086154937744141, "genuineness": 4.494794845581055, "identity": 0.6993695497512817, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude ruim. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/e35e039d5a23d83a3befb63dde6282d20f748d572a6cda645a3aa58d0b365c23.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "e381117eafcb39761bb602e9b91761a0d112bd8e0177e8144d5149b2496bf216", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1642e58446f91a02cf7e1928d31902902bf6f68f3e14447f552b7cadb04a8b4f", "generation_seconds_batch": 16.96245014993474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.04121798276901245, "target_z": -0.6406250240310761, "ce": 6.356205940246582, "genuineness": 4.457139015197754, "identity": 0.45351946353912354, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/e381117eafcb39761bb602e9b91761a0d112bd8e0177e8144d5149b2496bf216.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "e3ece605287de14eab4307fda0b385d6e966d00f76bb33b2f58a6e76d7733548", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d9de6032ec12458b38cc871cc37287045685a23bf0c9159161aa3970dc49e4d9", "generation_seconds_batch": 24.593255235929973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2731170356273651, "target_z": 0.13183596689515567, "ce": 5.4944257736206055, "genuineness": 4.582659721374512, "identity": 0.5930131673812866, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/e3ece605287de14eab4307fda0b385d6e966d00f76bb33b2f58a6e76d7733548.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "e3f721900526cb7250c5912f10515b69800cad89bea8c28539caddf19b5b5286", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5a8be46d2746929d8c9298a0cd132d1b00cc4e87f22e6f59b1052cd8b22ddee2", "generation_seconds_batch": 17.269432975910604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029517337679862976, "target_z": -0.4667968708517785, "ce": 6.165581703186035, "genuineness": 3.8044304847717285, "identity": 0.10218104720115662, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/e3f721900526cb7250c5912f10515b69800cad89bea8c28539caddf19b5b5286.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "e49202b554779273a8f5e73c627f96302b6950ce5630995f0940b141345675b5", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e5ddf6938429cd417ccaac2395e08bcfed3bfd67077134ee66aeffb0df673f00", "generation_seconds_batch": 24.245086793904193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08833096921443939, "target_z": -0.3222656114109986, "ce": 5.967014789581299, "genuineness": 4.7458367347717285, "identity": 0.7023950219154358, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/e49202b554779273a8f5e73c627f96302b6950ce5630995f0940b141345675b5.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "e49fcc896786260e70657dc584396709fe0eb647f21374a1543f9836b922ed57", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d2a379da1b4a190a73a521ef12ff1e5ffa3ef3a4ae43b9abaf961456cb01552a", "generation_seconds_batch": 21.68685894506052, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16542449593544006, "target_z": -0.13281251659288593, "ce": 6.117925643920898, "genuineness": 4.607763767242432, "identity": 0.7715125679969788, "hypothesis": "La porte 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_Bitterness/e49fcc896786260e70657dc584396709fe0eb647f21374a1543f9836b922ed57.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "e587386abe2ce533eb3401098fb915eaa86239a8ab5422a19aa30f514c03dee0", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "45d3e5d6265e8ae698cdcbcec05ea3f4fb4dbf140b87230214b172c6097409ac", "generation_seconds_batch": 17.087452477077022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17098794877529144, "target_z": -0.11914063773074868, "ce": 6.213237762451172, "genuineness": 4.419482707977295, "identity": 0.5881471633911133, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/e587386abe2ce533eb3401098fb915eaa86239a8ab5422a19aa30f514c03dee0.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "e63a019a947fba6ea0e0574315876de1b4174fbd2b05bc1225a64ed3a02b888d", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "37a29dcad5b234ea8e2acdc9ab5feb565cd10b993a94fac64f99767fb706fdfa", "generation_seconds_batch": 17.112980129080825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046207696199417114, "target_z": -0.4257812342653668, "ce": 6.086154937744141, "genuineness": 4.444586753845215, "identity": 0.8055019378662109, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/e63a019a947fba6ea0e0574315876de1b4174fbd2b05bc1225a64ed3a02b888d.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "e6439d1a51a37cfa8e35e438dc43da6cb2c69979036e939f63f4988d41d863c7", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a291c8081e2cbca604289e17142ba11d739a6606f82561bd8fbe90129c6c19f8", "generation_seconds_batch": 15.656238801078871, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2548370957374573, "target_z": 0.08691402166147473, "ce": 5.903473377227783, "genuineness": 4.231201171875, "identity": 0.4729093909263611, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/e6439d1a51a37cfa8e35e438dc43da6cb2c69979036e939f63f4988d41d863c7.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "15b7f19d9a66ba896d1f3d2582b0e4d6c4a5234887247bf476434264e4935ed7", "generation_seconds_batch": 19.429479795042425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06289803981781006, "target_z": -0.3847656342977378, "ce": 6.427689552307129, "genuineness": 4.325342178344727, "identity": 0.38883426785469055, "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_Bitterness/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "e7a22f41b3fc62b1b0661c510e67bd1ad5b9611dc66f0dc91f97166b95a357ff", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9986cffebf628f033b0fb27b8a17b13430c89ae3bc55599810f2f4e7e3660f09", "generation_seconds_batch": 26.31037823902443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11455865949392319, "target_z": -0.25781250743819023, "ce": 6.054384231567383, "genuineness": 4.362998008728027, "identity": 0.6162980794906616, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/e7a22f41b3fc62b1b0661c510e67bd1ad5b9611dc66f0dc91f97166b95a357ff.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "e82c74fb7644b3ae6080bb38da18dbd53dfea824ad6e6b813c280bad2240bd52", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e5e738fbf3c133a09c9ac4544099c615c44b178c9dd24bea8e9a6bd5b2de69ad", "generation_seconds_batch": 23.830030101002194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.046039342880249, "target_z": 2.0312499565151954, "ce": 5.764476776123047, "genuineness": 4.607763767242432, "identity": 0.6320724487304688, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/e82c74fb7644b3ae6080bb38da18dbd53dfea824ad6e6b813c280bad2240bd52.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": "e92370236f5b48509245de8cd235e2375bd9f8805a32d903b74a6d5c4af973c7", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d688542ce3947400dd842da2ef7ba2822d371183410fe848cc0f3f5300be5a39", "generation_seconds_batch": 23.374517517047934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12409600615501404, "target_z": -0.23437500343301088, "ce": 6.0305562019348145, "genuineness": 4.482243061065674, "identity": 0.3611130118370056, "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_Bitterness/e92370236f5b48509245de8cd235e2375bd9f8805a32d903b74a6d5c4af973c7.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "e995b21a533a0e78c52025fc938f45499c72f90b32b3e227441b320e9dae23bb", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1f9168d3e12b52412ca173d7d326904c899863089d2f1284a65736b32a180874", "generation_seconds_batch": 21.704922662000172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.053360700607299805, "target_z": -0.4082031199935258, "ce": 6.0305562019348145, "genuineness": 4.469690799713135, "identity": 0.6688171625137329, "hypothesis": "La porte 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_Bitterness/e995b21a533a0e78c52025fc938f45499c72f90b32b3e227441b320e9dae23bb.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "eeca5e4997165b39b84d61bae625685937ecb842ec5b619f8925f112bc44dbb6", "generation_seconds_batch": 16.332335310056806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06766670942306519, "target_z": -0.3730468914498438, "ce": 6.332377910614014, "genuineness": 4.582659721374512, "identity": 0.5653209090232849, "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_Bitterness/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "e9eb33cca85be3294fa99cd610f4c766586edd30a2f4f0cb54d369c1f8240851", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c77034fcab1a7b092eccecb5ce207377d709af7f9eee3a2ef2ec6db3e4454066", "generation_seconds_batch": 24.42755339795258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.049386799335479736, "target_z": -0.4179687634459593, "ce": 6.316492557525635, "genuineness": 4.68307638168335, "identity": 0.5876694917678833, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/e9eb33cca85be3294fa99cd610f4c766586edd30a2f4f0cb54d369c1f8240851.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "ea2bfcb03845e6d36b268eb5bbe8b406b36efc880a05d1a914dd4a18ced9bf25", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "af9005a83e198799c7283539558c76cd4982bb1f198898c412474e5f5727d2f6", "generation_seconds_batch": 19.204028920968994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1352229118347168, "target_z": -0.2070312457087364, "ce": 6.086154937744141, "genuineness": 4.519899368286133, "identity": 0.7032163143157959, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/ea2bfcb03845e6d36b268eb5bbe8b406b36efc880a05d1a914dd4a18ced9bf25.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "ea63ed76012acd8769ceacf648c290b540ddfdb626b17494a52cc4879c959d8e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cef439f2e639e8d6f361bbf0a5d62f45439241978ffb20c72c0e8aaf53e66f0c", "generation_seconds_batch": 20.622499261051416, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004658147692680359, "target_z": -0.5507812434200625, "ce": 6.284721851348877, "genuineness": 4.68307638168335, "identity": 0.33517077565193176, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/ea63ed76012acd8769ceacf648c290b540ddfdb626b17494a52cc4879c959d8e.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "ea8cafc3d0f488d29acb0b23c18122164cb17a64a5d530ffacd7badcaa58f362", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "41c596824df33b715836abbb604d86aa8d63d58ed5a5663a3a0ffdac79ac669b", "generation_seconds_batch": 23.30501281004399, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0986630842089653, "target_z": -0.2968750080103587, "ce": 6.284721851348877, "genuineness": 4.262581825256348, "identity": 0.34673020243644714, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/ea8cafc3d0f488d29acb0b23c18122164cb17a64a5d530ffacd7badcaa58f362.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "eac6aacf56b0ef37460781aaa651c7529d0b21e011db8db682b0027e90524856", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c7a823f9f134d3f6678d2b7d6a48d45cf5d6900d710a0bca503012ae7739c377", "generation_seconds_batch": 24.930891500087455, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009426817297935486, "target_z": -0.5624999862679565, "ce": 6.229123115539551, "genuineness": 4.557555198669434, "identity": 0.28466325998306274, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/eac6aacf56b0ef37460781aaa651c7529d0b21e011db8db682b0027e90524856.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "ead2f672c85b4665a9607e8d53e7ed4800d3709da24dffb377010ba188bee242", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "679e0a2b87fc48ea453baf3c1bec5083c1597af6d7092f1692860f4191b882fa", "generation_seconds_batch": 24.0646369230235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.015785053372383118, "target_z": -0.578125001144337, "ce": 6.078212261199951, "genuineness": 4.469690799713135, "identity": 0.40256667137145996, "hypothesis": "I found the l little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/ead2f672c85b4665a9607e8d53e7ed4800d3709da24dffb377010ba188bee242.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "ebaa182fd7344c6c69fbe855400e80a6774fbed7a3e32064afc585adff94df0a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "905ccf6911788805bbd62e5ad48bc46cd50c756aa79331ec2416f32784229e92", "generation_seconds_batch": 23.785910113016143, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17893573641777039, "target_z": -0.09960938744466444, "ce": 5.577824115753174, "genuineness": 4.482243061065674, "identity": 0.2974027991294861, "hypothesis": "J'ai trouvé la 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_Bitterness/ebaa182fd7344c6c69fbe855400e80a6774fbed7a3e32064afc585adff94df0a.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "ebd970c1f87a9722fdbdbc172deaac09b066ebc2490c406823338596a6411373", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "cad6c5584960cb9a04c8e86cc5a90ada48502dc329bb27e4d61a0fa1198189c8", "generation_seconds_batch": 17.77802512398921, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10422653704881668, "target_z": -0.2832031291482215, "ce": 6.252951145172119, "genuineness": 4.7332844734191895, "identity": 0.715382993221283, "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_Bitterness/ebd970c1f87a9722fdbdbc172deaac09b066ebc2490c406823338596a6411373.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "56d4e8bdfa8a35ed49bacfc7f554dee0e337bb8f940aa3fa61d64acd3dd1907f", "generation_seconds_batch": 16.82806360803079, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12012211233377457, "target_z": -0.244140628576053, "ce": 6.125868320465088, "genuineness": 4.3881025314331055, "identity": 0.7463847398757935, "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_Bitterness/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "ec07a8ca85b3155e33a2cb3322fb94264306954ac3d3a84214df32c11e55de13", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "71635278442f441faaca2c667ecbcdda24f20c969884c08fbac8a2e397bc9154", "generation_seconds_batch": 24.29915293806698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10263697803020477, "target_z": -0.2871093828673166, "ce": 6.006728172302246, "genuineness": 4.833701133728027, "identity": 0.776139497756958, "hypothesis": "La porte 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_Bitterness/ec07a8ca85b3155e33a2cb3322fb94264306954ac3d3a84214df32c11e55de13.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "ed5896c5212eeb8ee67ce85e85a83875158380c8b5f58b72bbf17db5c2937ac4", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3a34e42db23bdc6a2f57f2557d98e6bf1b72e86a1215459a3a2d5b93bb2c41bf", "generation_seconds_batch": 22.56569595192559, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1940365433692932, "target_z": -0.06249998626795648, "ce": 5.879645347595215, "genuineness": 4.507347106933594, "identity": 0.4214915633201599, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/ed5896c5212eeb8ee67ce85e85a83875158380c8b5f58b72bbf17db5c2937ac4.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "ed83dc8e217703defe7c0367682223b31fc1c88a53f34157533f29b62fbc9555", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1d3cb0c0a7f66274ba1ad002c67cfdf0d8a369ce4b2b1f24397ed2ecca868fff", "generation_seconds_batch": 17.324337125988677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15111848711967468, "target_z": -0.16796874513656793, "ce": 5.557967185974121, "genuineness": 4.6203155517578125, "identity": 0.560893177986145, "hypothesis": "He encontrado la cajita, estaba junto a la ventana, vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/ed83dc8e217703defe7c0367682223b31fc1c88a53f34157533f29b62fbc9555.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": "eda198ceb6e692e63d1aa1c6ce2c653cbbc114b7331188d7ccec1a721466c4d8", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9dac39048d880101c530e3fbed2838de9f644734b27f6384023cbef0ef4ef0da", "generation_seconds_batch": 18.585794584010728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.060513705015182495, "target_z": -0.3906250057216848, "ce": 6.23706579208374, "genuineness": 4.582659721374512, "identity": 0.7853245139122009, "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_Bitterness/eda198ceb6e692e63d1aa1c6ce2c653cbbc114b7331188d7ccec1a721466c4d8.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "ee2b11dc85b8fec1c08b9a09698bf865804c22fbc888a07164aff38de0e56dba", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b4518127a0bde19f7cf917bd2955a91dc75c1a1eea5790ff5d5aaa8ca922b779", "generation_seconds_batch": 19.954143104027025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054950252175331116, "target_z": -0.404296884583822, "ce": 6.324435234069824, "genuineness": 4.406930446624756, "identity": 0.5448917150497437, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/ee2b11dc85b8fec1c08b9a09698bf865804c22fbc888a07164aff38de0e56dba.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "ee752a52808357eb0a7be695126483a33cb2c2e18d595dc0b8374e791dc5351c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "eb3e47829088372e58a9263ff02f6671646d9eda5b57323deb7c06df3bd5ea5a", "generation_seconds_batch": 22.645195971941575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4275331497192383, "target_z": 2.968749970247239, "ce": 5.919358730316162, "genuineness": 4.319066047668457, "identity": 0.11221857368946075, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/ee752a52808357eb0a7be695126483a33cb2c2e18d595dc0b8374e791dc5351c.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "eeaa0ecb94ec1a8800dac04f8c4043f7fc03d51fbea11d67a7f350d9e9542d10", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "854098e4e31fabd9e481e05707086a461f84988e467a0ca6e2590f827df85071", "generation_seconds_batch": 15.14416466106195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14317069947719574, "target_z": -0.18749999542265217, "ce": 6.133810997009277, "genuineness": 4.6956281661987305, "identity": 0.21238330006599426, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/eeaa0ecb94ec1a8800dac04f8c4043f7fc03d51fbea11d67a7f350d9e9542d10.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "ef0c04400c8779504e8c94fb545f194f4440a7bb948b4dd682496f471e451501", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2bfad2fd7cade4989d7ed5bbaed39cd377a98c4dbb0a6a4c352c06056818b309", "generation_seconds_batch": 22.837369419983588, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11853255331516266, "target_z": -0.24804688229514812, "ce": 6.260893821716309, "genuineness": 4.519899368286133, "identity": 0.44656217098236084, "hypothesis": "De deur staat nog open. Ik heb 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_Bitterness/ef0c04400c8779504e8c94fb545f194f4440a7bb948b4dd682496f471e451501.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "f01906e648beca7ca3f6338f04f5fd83c298160710c7cdbfef00bb8104550942", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3fac224291738c3e9c68a3adf9d561f20f17e2ffd05e97765b679e0568ecf75b", "generation_seconds_batch": 23.71656840702053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14078636467456818, "target_z": -0.19335936684659916, "ce": 5.585766792297363, "genuineness": 4.532451152801514, "identity": 0.6518639922142029, "hypothesis": "Hmm he encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f01906e648beca7ca3f6338f04f5fd83c298160710c7cdbfef00bb8104550942.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": "f0b0bcd334a1db658adaa51551c577093af61b9fb0dccfd28e35036fdba4e729", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Your message arrived after I had left.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a5c8637bf9694a51dea0725e3637de88eb459b83b37339874f665ec5320db386", "generation_seconds_batch": 23.630005580955185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2361598163843155, "target_z": 0.04101563658641172, "ce": 6.507116317749023, "genuineness": 4.545003414154053, "identity": 0.49287253618240356, "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_Bitterness/f0b0bcd334a1db658adaa51551c577093af61b9fb0dccfd28e35036fdba4e729.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "f0e792c40db98b2a8ba51e7ec6f696e0e294a9b8c65951c4b99ca36af5602d44", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0ac5b707e28cf0d07df8cfcd85c512145f119305be017537c39abfa6b809a001", "generation_seconds_batch": 24.574886864051223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.040644243359565735, "target_z": -0.439453113127504, "ce": 6.006728172302246, "genuineness": 4.582659721374512, "identity": 0.45303720235824585, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f0e792c40db98b2a8ba51e7ec6f696e0e294a9b8c65951c4b99ca36af5602d44.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "f10e287f6d7514cebb2e1e21e74caf87e023b19b59e76ab2cebef9ae7bf5b7d9", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c44982d3beb07b1a8f0d5b0d9ec9d5eaf8e2f6f253c03841266e6316b9a5871a", "generation_seconds_batch": 16.50593022198882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1455550342798233, "target_z": -0.18164062399870515, "ce": 6.229123115539551, "genuineness": 4.469690799713135, "identity": 0.31963491439819336, "hypothesis": "The 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_Bitterness/f10e287f6d7514cebb2e1e21e74caf87e023b19b59e76ab2cebef9ae7bf5b7d9.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "f139f154e3d8826b3728ac4a310cc26e4240dce2299fb91801da493fb74224db", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "314e4c425092eae4d4cb1ca9a946e9972498b12a5a0edb336785b7c43b1ba4ad", "generation_seconds_batch": 22.871757179964334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12886467576026917, "target_z": -0.2226562605851169, "ce": 5.700935363769531, "genuineness": 4.7332844734191895, "identity": 0.5864791870117188, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f139f154e3d8826b3728ac4a310cc26e4240dce2299fb91801da493fb74224db.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "f1415c3afc19c12c131506c3303782204ab8c77bd9d1bafceb1f1682f45edb57", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "49aee7412d20fc1a85cd040a5e61e32ba5ad424cac484924c393b074aaff33ba", "generation_seconds_batch": 22.80264844908379, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08753618597984314, "target_z": -0.3242187474252418, "ce": 6.070269584655762, "genuineness": 4.15588903427124, "identity": 0.336853563785553, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f1415c3afc19c12c131506c3303782204ab8c77bd9d1bafceb1f1682f45edb57.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "f18f2a75a216df1b8a258a7f2e7532d765b5765f644f4727b9ef2cdc9f15bb0f", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f0c17ea45a32f7b2e07ba6664f6be64d9ea34ec11cf5c2319211019d8a182027", "generation_seconds_batch": 15.419242302072234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00011052191257476807, "target_z": -0.5390625005721685, "ce": 6.09409761428833, "genuineness": 4.570107460021973, "identity": 0.32610467076301575, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f18f2a75a216df1b8a258a7f2e7532d765b5765f644f4727b9ef2cdc9f15bb0f.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "f1a8683f697ac7c0335cffe20fd2a967f3a3d731db45965f2c07fc81188a388c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8dd4362ddba7fdd27d26e608aa505c518c723595b5c483fb38c8f79f66e984fc", "generation_seconds_batch": 24.585604504914954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19165220856666565, "target_z": -0.06835935769190347, "ce": 5.9431867599487305, "genuineness": 4.545003414154053, "identity": 0.561468243598938, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f1a8683f697ac7c0335cffe20fd2a967f3a3d731db45965f2c07fc81188a388c.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "f1dd570eecde30d20d1e3ff79897441df6a4e64890a1835dad74fe33b63d856a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "44baa685eecbeb363efec8978f11cb171e7719d51b009d23ccf898f30f77d8f6", "generation_seconds_batch": 21.717964767012745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04143901169300079, "target_z": -0.4375000137320435, "ce": 6.300607204437256, "genuineness": 4.607763767242432, "identity": 0.7289047837257385, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f1dd570eecde30d20d1e3ff79897441df6a4e64890a1835dad74fe33b63d856a.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "c467b90163ace73b0aa55b523039ecaf03f86a244d9575963a22e4f437713ba2", "generation_seconds_batch": 16.60086841590237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07481972873210907, "target_z": -0.35546874055922006, "ce": 6.205295085906982, "genuineness": 4.570107460021973, "identity": 0.5466383099555969, "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_Bitterness/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "f25880e99219eb7507a9360738b86dd64e9055fa66d615704845a4feefdb65b6", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2b54b3b74c00aaf97b2187e4d5ccfd0c84a51aa44ecdafb27fef3d8fecc92a3c", "generation_seconds_batch": 24.292780222021975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03031212091445923, "target_z": -0.46484373483753527, "ce": 6.141753673553467, "genuineness": 4.7081804275512695, "identity": 0.5972845554351807, "hypothesis": "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_Bitterness/f25880e99219eb7507a9360738b86dd64e9055fa66d615704845a4feefdb65b6.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "f29efcc680aa43dfa2f6590fb2fb97227c03d36df5179cd3aeefe03406666e54", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4441df0aa0571e57c24a541fa1eb9e0703a69dcdb571b9431c24ea0d9765e20c", "generation_seconds_batch": 17.70355972892139, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.143965482711792, "target_z": -0.18554685940840893, "ce": 5.919358730316162, "genuineness": 4.7081804275512695, "identity": 0.7370299696922302, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f29efcc680aa43dfa2f6590fb2fb97227c03d36df5179cd3aeefe03406666e54.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": "f2f1b22df6d39837182fe71c45a634c1261d1935a313513f6a234241e408d05b", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0d499447f91f34b7a704759e242118605eaf8cc3892ff19f1b5fdf9663c6139a", "generation_seconds_batch": 20.674130468978547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15509238839149475, "target_z": -0.15820310168413443, "ce": 5.8875885009765625, "genuineness": 4.6705241203308105, "identity": 0.6321061849594116, "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_Bitterness/f2f1b22df6d39837182fe71c45a634c1261d1935a313513f6a234241e408d05b.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "f319ec044b97d18d0e698d825da1110223a44fe151aa70578b7c8d0aa8451cc3", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "265695ec3126ecfd0f42e3a39e6e0c599f970c433c6bc902b25a42c454280ee4", "generation_seconds_batch": 23.079100886010565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.018964171409606934, "target_z": -0.5859375085825272, "ce": 6.324435234069824, "genuineness": 4.507347106933594, "identity": 0.40121060609817505, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f319ec044b97d18d0e698d825da1110223a44fe151aa70578b7c8d0aa8451cc3.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "f32840c2a18d4cda26f2f974b89ec942f1b399c3b3c547e72cc434e17dd88d12", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "24fc2ca8dd373560c9ce76715ceb86100c6fb83da0ab27727e21b519dafd4c4e", "generation_seconds_batch": 23.15789654001128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05733458697795868, "target_z": -0.398437513159875, "ce": 6.284721851348877, "genuineness": 4.231201171875, "identity": 0.6926039457321167, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f32840c2a18d4cda26f2f974b89ec942f1b399c3b3c547e72cc434e17dd88d12.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "f4052a1e2871e1f3a26787c05dfeb039b1058f7849ba01505442cf37a14463f7", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4f0d23cbb579b721603ca148a1e63f38d4cf35f375c632b5f2d94a11ecd9c4ff", "generation_seconds_batch": 22.70804410101846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08594663441181183, "target_z": -0.3281249828349456, "ce": 6.070269584655762, "genuineness": 4.607763767242432, "identity": 0.7155934572219849, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f4052a1e2871e1f3a26787c05dfeb039b1058f7849ba01505442cf37a14463f7.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "f4915817d0f02262ab62af7e7c7bf13a62a8f7285c8ba455e54b97ed31647a9a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e64e0bfc61962fe168829ebbe8b8fb5b97f003ae5ca054f3917a57136950a3ba", "generation_seconds_batch": 23.079717120039277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08435706794261932, "target_z": -0.3320312548634321, "ce": 5.95112943649292, "genuineness": 4.758388519287109, "identity": 0.8702807426452637, "hypothesis": "Hmm. J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f4915817d0f02262ab62af7e7c7bf13a62a8f7285c8ba455e54b97ed31647a9a.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "f4a301a7d581527b745b580ed795188d6374b56df704a686d7294213aba4d928", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "196eed7bb0c906af42289a475e1c3a6b5f28af3306ccff35526d007e9b1eb681", "generation_seconds_batch": 22.236621102900244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05574503540992737, "target_z": -0.4023437485695788, "ce": 5.831989288330078, "genuineness": 4.758388519287109, "identity": 0.6092000007629395, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f4a301a7d581527b745b580ed795188d6374b56df704a686d7294213aba4d928.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "f50eac61ffc12336e43e8d9e249a348facc611182c2670334cd4a82e4717ce3a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0dea92feb5751083455b2c12f9b2fd86c552a84dd4bdf2cda9f54d66fd04eef5", "generation_seconds_batch": 16.62556344200857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7567398548126221, "target_z": 1.3203124021591899, "ce": 6.0146708488464355, "genuineness": 4.381826400756836, "identity": 0.36550575494766235, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f50eac61ffc12336e43e8d9e249a348facc611182c2670334cd4a82e4717ce3a.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "f530dd9ef0eb8aeafe7a2623b30af67cb0ae694205a1940a15be504c0d7c3702", "bucket": "emo_Bitterness", "phase": "wording", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "52d8a113e5f5fd8dd52e0249999340f1fdaefc25c8cd93030fb485df341550ea", "generation_seconds_batch": 17.27816205995623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035875558853149414, "target_z": -0.4511718925941808, "ce": 6.022613525390625, "genuineness": 4.545003414154053, "identity": 0.6539154052734375, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f530dd9ef0eb8aeafe7a2623b30af67cb0ae694205a1940a15be504c0d7c3702.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "f560afe8d9d52ab41a4444dcd3ba0e144b9b88ad0f207fe1447292392550e070", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4ce5a8db2d188eeb4f713fda554caa4e116ec7f455a5d690902a670c57b05e3e", "generation_seconds_batch": 22.21567549498286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003289639949798584, "target_z": -0.5312499931339782, "ce": 6.316492557525635, "genuineness": 4.532451152801514, "identity": 0.32553499937057495, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f560afe8d9d52ab41a4444dcd3ba0e144b9b88ad0f207fe1447292392550e070.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "f59d95493d4a35f27868a7bef0086dda1bcd46fb27e48d14715e9f327d702ec3", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e726c6d96df167927374373a6ac1d46ba6271ab2d67babc7d4f88e58e6e8e7aa", "generation_seconds_batch": 22.156160891987383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3112664222717285, "target_z": 0.22558598291587312, "ce": 5.879645347595215, "genuineness": 4.293961524963379, "identity": 0.44179826974868774, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f59d95493d4a35f27868a7bef0086dda1bcd46fb27e48d14715e9f327d702ec3.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "f614777c1c5231414ef840b8285ce8b347a29982deeea94ef1e6ab953840042d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "730ec67e0064de82883c96129af7c7d7bac386453f309d6512dd4d2fb2ee3104", "generation_seconds_batch": 23.311395670985803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11853255331516266, "target_z": -0.24804688229514812, "ce": 5.974957466125488, "genuineness": 4.432034492492676, "identity": 0.7091617584228516, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f614777c1c5231414ef840b8285ce8b347a29982deeea94ef1e6ab953840042d.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "f61758e685589ff8c23443e3370abd42feb3e8e7712ee19aacebef5201425d4e", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e182f02983396ddd39d34a0c64987f0e7ab4b59a2959fc25cef2c84889504b85", "generation_seconds_batch": 22.966008196002804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2186746746301651, "target_z": -0.001953136014243242, "ce": 5.982900142669678, "genuineness": 4.3504462242126465, "identity": 0.4220570921897888, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f61758e685589ff8c23443e3370abd42feb3e8e7712ee19aacebef5201425d4e.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "f627205b6662c6829a5716953db109e3c37b419673566bc58a22fccbeb022793", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5b7f52eb1ee352e7992bbf9530e101376d9e5c93fb7cd506514a56086ca46d9c", "generation_seconds_batch": 23.444103364017792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1749618500471115, "target_z": -0.1093749942783152, "ce": 5.911416053771973, "genuineness": 4.582659721374512, "identity": 0.7884902954101562, "hypothesis": "La porte 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_Bitterness/f627205b6662c6829a5716953db109e3c37b419673566bc58a22fccbeb022793.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "f68c5beef713f0247220fb26855a54869f27e5f55d85d88188a45f8ee275ac39", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "12d2d191326fcea4f992e53605f090ddac8d464d037991bc05a097b7794490fa", "generation_seconds_batch": 24.585604504914954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12489078938961029, "target_z": -0.23242186741876764, "ce": 5.879645347595215, "genuineness": 4.519899368286133, "identity": 0.7408624887466431, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f68c5beef713f0247220fb26855a54869f27e5f55d85d88188a45f8ee275ac39.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "f6b7e562d37fbd4ea13b30e0c4241b6aabff2e4d1cd46968ffed8f98c1f4e2d8", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ffe9f76673a65dffc7dc29f3d2270ee44192f1357c4e1b6c18cf6ba99c0e24d1", "generation_seconds_batch": 18.082657355000265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11376388370990753, "target_z": -0.25976562514304213, "ce": 5.661221981048584, "genuineness": 4.595211505889893, "identity": 0.5004812479019165, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f6b7e562d37fbd4ea13b30e0c4241b6aabff2e4d1cd46968ffed8f98c1f4e2d8.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "f70b0aecd02f9193dec4fdc0349393b67e83be1308e6a2194303111ffd9db77c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0c5fbe779973ff26e3b2d54ad9c43fc8a189505767508400901966e92cfd29b7", "generation_seconds_batch": 25.801949035958387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12489078938961029, "target_z": -0.23242186741876764, "ce": 5.649308204650879, "genuineness": 4.545003414154053, "identity": 0.6236844062805176, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f70b0aecd02f9193dec4fdc0349393b67e83be1308e6a2194303111ffd9db77c.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "f78163ba24a831b3309e182572c44c749396c9f8ac0a01eb4cbe4e54dd32b141", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "110ede1c85a72d0757c2f9ccd3bcc319e1e620b362160c5e2f84a2a9cb9024bc", "generation_seconds_batch": 24.328037773026153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12727512419223785, "target_z": -0.22656249599482065, "ce": 5.879645347595215, "genuineness": 4.808597087860107, "identity": 0.7623332738876343, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f78163ba24a831b3309e182572c44c749396c9f8ac0a01eb4cbe4e54dd32b141.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "f78ed835637e4c8cb9a2f963c7eff7a73f9881dc68a95343b1341e224d47e8cd", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "dc7ade8cac6b80ef7739ecb1c85c468827b7d2facf4f1de0aadf764e72492611", "generation_seconds_batch": 26.978992001037113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2743091881275177, "target_z": 0.13476561598834644, "ce": 5.474569320678711, "genuineness": 4.319066047668457, "identity": 0.6240062713623047, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f78ed835637e4c8cb9a2f963c7eff7a73f9881dc68a95343b1341e224d47e8cd.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "f798e3a550ae5973f36a0a202c24e8199307f3abf0d08424486f7f9856dff573", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ff499c2347e971459a2a2af8ece272798b7d219f564c8944452f64c57cca7781", "generation_seconds_batch": 23.830030101002194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16224539279937744, "target_z": -0.14062498741229343, "ce": 5.6254801750183105, "genuineness": 4.306513786315918, "identity": 0.648844838142395, "hypothesis": "Ah, j'ai trouvé la petite boîte, les tébrettes de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.21052631578947367, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f798e3a550ae5973f36a0a202c24e8199307f3abf0d08424486f7f9856dff573.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "aa2e83f6400f34d26fbf2b8afef02555557240574e402d22afbced338162afad", "generation_seconds_batch": 16.37285480706487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.001700073480606079, "target_z": -0.5351562651624647, "ce": 6.268836498260498, "genuineness": 4.582659721374512, "identity": 0.6715226769447327, "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_Bitterness/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.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_Bitterness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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": "d8cec1b3661d15fc6124f6a20a547f0d75d6b9f96f4ee44108939e8161d1c4cc", "generation_seconds_batch": 17.782095110975206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06369282305240631, "target_z": -0.38281249828349456, "ce": 6.38003396987915, "genuineness": 4.469690799713135, "identity": 0.5358589887619019, "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_Bitterness/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Bitterness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Bitterness-nl-0", "key": "f8c968ae4c3fff88f431e17c8e854b19d7acffb9bbda1c1431f3795e491cb0d9", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De deur staat nog open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a7069d4b5efed541bdc641d4c08a7724221d99b3944bf0ea920e38c5763f3073", "generation_seconds_batch": 23.637818983988836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2361598163843155, "target_z": 0.04101563658641172, "ce": 6.149696350097656, "genuineness": 4.425758361816406, "identity": 0.5243191123008728, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f8c968ae4c3fff88f431e17c8e854b19d7acffb9bbda1c1431f3795e491cb0d9.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": "f8e8f104e0df84db85550dc7f874eb3ebce1bafde9fa075082d16d04e61184d7", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "57124c2729e1017456ecddae2b0a78cd01c82b55abddf209fd9b382effe09cc2", "generation_seconds_batch": 24.66101698903367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28980737924575806, "target_z": 0.17285156686278466, "ce": 5.831989288330078, "genuineness": 4.545003414154053, "identity": 0.6314170360565186, "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_Bitterness/f8e8f104e0df84db85550dc7f874eb3ebce1bafde9fa075082d16d04e61184d7.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "f903b5f4ea0eafd911fc6713d0211f5dfc7e30ac6bedf11dbd6619aeaf1dfda6", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "86d1fffd16dc1e47780c7a8d6bae74ce9b8f32f5bb3f8ed0123569fde0a4de15", "generation_seconds_batch": 24.574886864051223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07720406353473663, "target_z": -0.3496093691352731, "ce": 5.824047088623047, "genuineness": 4.306513786315918, "identity": 0.15206220746040344, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f903b5f4ea0eafd911fc6713d0211f5dfc7e30ac6bedf11dbd6619aeaf1dfda6.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": "f90fddb0a1776c6b67ad5f790b0cc768f87a7e1fac992f3ab4e544683f93e2ec", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8d76ef6a7aa88fc876b2ecf62250c30b13526f3a3b80334ee7a9ff2fa34b2170", "generation_seconds_batch": 23.902683955035172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14158114790916443, "target_z": -0.19140623083235592, "ce": 5.831989288330078, "genuineness": 4.632867813110352, "identity": 0.8274097442626953, "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_Bitterness/f90fddb0a1776c6b67ad5f790b0cc768f87a7e1fac992f3ab4e544683f93e2ec.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "f9294bb438b72ebe49c6aafdcf8fa3270da17a484d8225d3685f7e143c1015a7", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6ee5a1db76a4422a8467e1b832a23d7fc45a82815fc49bf4b3c4046b4b2803b9", "generation_seconds_batch": 25.025806077057496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05256591737270355, "target_z": -0.41015625600776906, "ce": 6.165581703186035, "genuineness": 4.143336772918701, "identity": 0.26684579253196716, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f9294bb438b72ebe49c6aafdcf8fa3270da17a484d8225d3685f7e143c1015a7.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "f97eb75509f47cf02cfc60422abc59d99d29cde10bd6787a4b51a369567f472c", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fdf4e69813d79f9c7a0609b6acffa26a221cf107ac4c0ed9f77583f6eba3ab06", "generation_seconds_batch": 21.717964767012745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06766670942306519, "target_z": -0.3730468914498438, "ce": 6.165581703186035, "genuineness": 4.7458367347717285, "identity": 0.7090778350830078, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/f97eb75509f47cf02cfc60422abc59d99d29cde10bd6787a4b51a369567f472c.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": "fa062bfdcdc509112077643e591d077b4da26b72def503e280c8f2f2e2d7abd5", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e3d94abd95a57e71591e3a83aea92f6107c61b7ef496018f820355bb92d13469", "generation_seconds_batch": 16.73767429997679, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17019318044185638, "target_z": -0.1210937371262092, "ce": 5.824047088623047, "genuineness": 4.281409740447998, "identity": 0.4125772714614868, "hypothesis": "Oemant heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het naar de lunch terug.", "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_Bitterness/fa062bfdcdc509112077643e591d077b4da26b72def503e280c8f2f2e2d7abd5.mp3" }, { "id": "emo_Bitterness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Bitterness-de-0", "key": "fa126a07cfb3e7964bf88d59e3bbe74cb0b9bca6e8d7a798e8e857b9e15c2a9d", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Tür ist noch offen.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "61325b2304b0eff7824e53717c0ca43d5a02eccd1af1cbdb9774998b017963e3", "generation_seconds_batch": 23.430117720970884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17257751524448395, "target_z": -0.1152343657022622, "ce": 5.77639102935791, "genuineness": 4.406930446624756, "identity": 0.6244724988937378, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/fa126a07cfb3e7964bf88d59e3bbe74cb0b9bca6e8d7a798e8e857b9e15c2a9d.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "fa2991adb4873aacc7b6395926c46b99ec0e0c8701ca7d4fd293fe9c89904540", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1aae0a34e2c9f6b442acbd6c489c8fc5d92ac4e845793de7caa93f9f4347dc02", "generation_seconds_batch": 23.10640240693465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.015785053372383118, "target_z": -0.578125001144337, "ce": 6.435632705688477, "genuineness": 4.432034492492676, "identity": 0.39296209812164307, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/fa2991adb4873aacc7b6395926c46b99ec0e0c8701ca7d4fd293fe9c89904540.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "fad2cb8471f3dbf40db4c2062e0ee76238690997c68934a8944c0938d282f83b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3b796286e8ead03c0cee35ca95d546e7ef7aa6fb13da4151fb9a188233f3d070", "generation_seconds_batch": 22.625727439997718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1558871567249298, "target_z": -0.15625000228867392, "ce": 5.855817794799805, "genuineness": 4.632867813110352, "identity": 0.779369592666626, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/fad2cb8471f3dbf40db4c2062e0ee76238690997c68934a8944c0938d282f83b.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "fb77b594eaa42ed9d724fe36886f5c05d259f0e967c07debeafe936a8e2ddb6a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e181150da114e1b14a39be693349903a278a4c1ba439c40fb0eba5e05eceaf56", "generation_seconds_batch": 23.134968134923838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14078636467456818, "target_z": -0.19335936684659916, "ce": 5.998785495758057, "genuineness": 4.758388519287109, "identity": 0.8554959297180176, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/fb77b594eaa42ed9d724fe36886f5c05d259f0e967c07debeafe936a8e2ddb6a.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "fb8e540c799751922f28761384ce870bc844b162c5abc81daf8c63b4514772c7", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3c37bd21a38ba3d5fbd3a198feb4b0aa5bc7156fc37ad95c6a29f6ac5c059fd0", "generation_seconds_batch": 23.71656840702053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10502132028341293, "target_z": -0.28124999313397825, "ce": 5.550024509429932, "genuineness": 4.7332844734191895, "identity": 0.6901723146438599, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/fb8e540c799751922f28761384ce870bc844b162c5abc81daf8c63b4514772c7.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "fb9130ba952095d9fff1d1401205e4fbe4bb707584e482d300b5c56beb2f2499", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "195a568eb91c00d9c7cd63b570f0fb2a4628541cfae6a29bb87a5f361ec5b97b", "generation_seconds_batch": 21.72680138493888, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15668193995952606, "target_z": -0.15429686627443068, "ce": 5.395142555236816, "genuineness": 4.293961524963379, "identity": 0.47005078196525574, "hypothesis": "Una puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.13333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/fb9130ba952095d9fff1d1401205e4fbe4bb707584e482d300b5c56beb2f2499.mp3" }, { "id": "emo_Bitterness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Bitterness-es-1", "key": "fbe8b83660c76a4a6b781d2e5517d586d72783feea670b2ff9613531e6325aee", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] He encontrado la cajita.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e2fb7f8fca49b16376def752295b6734b81d5e2dfeaee699135fffbc71a0cac4", "generation_seconds_batch": 16.071710949065164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02077476680278778, "target_z": -0.488281257152106, "ce": 6.141753673553467, "genuineness": 4.8588056564331055, "identity": 0.8006284236907959, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/fbe8b83660c76a4a6b781d2e5517d586d72783feea670b2ff9613531e6325aee.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "fc08528a2564cdd0196d75a3147d6b077da93a19e00f372019a021589a06ab2a", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7398a832812e2249b9d067464bff247f19ddc59d139b30439a2019ceb4c5a830", "generation_seconds_batch": 24.41931577399373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06289803981781006, "target_z": -0.3847656342977378, "ce": 6.157639026641846, "genuineness": 4.1998209953308105, "identity": 0.7898675799369812, "hypothesis": "La porte 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_Bitterness/fc08528a2564cdd0196d75a3147d6b077da93a19e00f372019a021589a06ab2a.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "fdb3963e52b9e2d73ffb984cde13d0810bff392bd011af760f3926d4986dcd87", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "541b3a901353e4180172116a0628ff62e093cd91ea4ee6c7319a2e9b8b7b83c1", "generation_seconds_batch": 17.70355972892139, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11455865949392319, "target_z": -0.25781250743819023, "ce": 5.760505676269531, "genuineness": 4.68307638168335, "identity": 0.7764527201652527, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/fdb3963e52b9e2d73ffb984cde13d0810bff392bd011af760f3926d4986dcd87.mp3" }, { "id": "emo_Bitterness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Bitterness-en-1", "key": "fdd28b187fe015b9b662aea1e6ed163063a4b3709cef92904610565b7986319b", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] I found the little box.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] It was beside the old window.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a5c3591d4aceae8a626233ce64d40603892a8ac64617ccd034eaefb246c464cc", "generation_seconds_batch": 18.470095761003904, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06369282305240631, "target_z": -0.38281249828349456, "ce": 5.772419452667236, "genuineness": 4.21237325668335, "identity": 0.28014615178108215, "hypothesis": "I f found a little box. It was beside the old window. We can look inside together.", "wer": 0.125, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/fdd28b187fe015b9b662aea1e6ed163063a4b3709cef92904610565b7986319b.mp3" }, { "id": "emo_Bitterness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Bitterness-es-0", "key": "fe3519a0f5601baaeabdeb31f816ec0b6db55b827126cb0ea449e2d7f999bfc4", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La puerta sigue abierta.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "63970ff51254ff3452ded573cf1997fa7a0cfcf172895d48f12892eca611f04d", "generation_seconds_batch": 16.673365670023486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1542975902557373, "target_z": -0.1601562743171604, "ce": 5.5539960861206055, "genuineness": 4.344170093536377, "identity": 0.5011907815933228, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/fe3519a0f5601baaeabdeb31f816ec0b6db55b827126cb0ea449e2d7f999bfc4.mp3" }, { "id": "emo_Bitterness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Bitterness-fr-0", "key": "fe801460ca13198aa63c8cd0aa3f82cd2b2e6dd632b98aac27cbb2a818c72b78", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La porte est encore ouverte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b06b42bc539889337242f1d94b7841de0cefd94839ebe55897cc97c509181584", "generation_seconds_batch": 28.305341074010357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11137954890727997, "target_z": -0.2656249965669891, "ce": 6.062326908111572, "genuineness": 4.582659721374512, "identity": 0.7195549011230469, "hypothesis": "La porte 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_Bitterness/fe801460ca13198aa63c8cd0aa3f82cd2b2e6dd632b98aac27cbb2a818c72b78.mp3" }, { "id": "emo_Bitterness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Bitterness-en-0", "key": "fed0877db44e65bb1499311db17577db6473df24456c7e5a6b3ab7989c93b1e1", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] The door is still open.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c9bf3799e3c17bfc73fd6d919e5ff92add83b08fd656ee9c87d3c919189b523e", "generation_seconds_batch": 24.032985058031045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11296910792589188, "target_z": -0.261718742847894, "ce": 6.181467056274414, "genuineness": 4.231201171875, "identity": 0.25415492057800293, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/fed0877db44e65bb1499311db17577db6473df24456c7e5a6b3ab7989c93b1e1.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": "ff24f9634a9e966127374f43d9376a2fd8392c13b54ef604b3285cb072db1803", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cf701c37cff516fb5867cac4cbc6477560515f5282796a1e63af99d47fc16d71", "generation_seconds_batch": 17.524931850959547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14078636467456818, "target_z": -0.19335936684659916, "ce": 6.054384231567383, "genuineness": 4.65797233581543, "identity": 0.6076902151107788, "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_Bitterness/ff24f9634a9e966127374f43d9376a2fd8392c13b54ef604b3285cb072db1803.mp3" }, { "id": "emo_Bitterness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Bitterness-de-1", "key": "ffa81332a6ca17f954155742bf8c6b8e04465c67d815e452933aea32fb7e4312", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ee16b2ab9a15ab0b2f0cb42a1901a661a87d2c84af67b98144f9aa72c39aeeb9", "generation_seconds_batch": 23.785309836035594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12250644713640213, "target_z": -0.238281257152106, "ce": 5.7684478759765625, "genuineness": 4.457139015197754, "identity": 0.5561996698379517, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/ffa81332a6ca17f954155742bf8c6b8e04465c67d815e452933aea32fb7e4312.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": "ffabd027b68785880985bd96895c2e1bb66cd76275390e7bc092e10b2683460b", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [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": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "80061479b41f84e07ab14ecd0bec50b0c1ca3c84d62db95011b9774a19ec0dbd", "generation_seconds_batch": 22.26077409205027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24410760402679443, "target_z": 0.06054688687249596, "ce": 5.681078910827637, "genuineness": 4.519899368286133, "identity": 0.6322556138038635, "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_Bitterness/ffabd027b68785880985bd96895c2e1bb66cd76275390e7bc092e10b2683460b.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": "ffc003a08758830ba4915cce80527495ed35a37d10eaf267ff60ce771b4aa75c", "bucket": "emo_Bitterness", "phase": "heldout", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5a5dbfdb82b4d658e3719319f3049da00bd47806d29de5663945251660289f91", "generation_seconds_batch": 16.85415126301814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16621927917003632, "target_z": -0.1308593805786427, "ce": 6.0146708488464355, "genuineness": 4.482243061065674, "identity": 0.5934581756591797, "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_Bitterness/ffc003a08758830ba4915cce80527495ed35a37d10eaf267ff60ce771b4aa75c.mp3" }, { "id": "emo_Bitterness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Bitterness-nl-1", "key": "ffcfdeb93bf87acab19b71d38a6e942b9fc7d00f280bc5f45d57b09237f41068", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c6cdc680bc4f7e446757b4061546d382ceded88542449db8e1d96c8d16467126", "generation_seconds_batch": 16.07311039196793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1423759162425995, "target_z": -0.1894531314368954, "ce": 6.205295085906982, "genuineness": 4.381826400756836, "identity": 0.7714117765426636, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/ffcfdeb93bf87acab19b71d38a6e942b9fc7d00f280bc5f45d57b09237f41068.mp3" }, { "id": "emo_Bitterness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Bitterness-fr-1", "key": "ffe3c165412f0713ee2d504c7fee5399c4e642c71c2f8c6e08a43626894a69a7", "bucket": "emo_Bitterness", "phase": "grid", "candidate": "manual-564f1f7c16dd", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the energy from outright anger to profound, wounded disappointment; the bitterness should feel internal and brittle.\nSCRIPT:\n(Begin with a slightly constricted throat sound, suggesting the words are physically difficult to produce.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Modulate the volume very slightly, a barely perceptible dip in projection that suggests withdrawal.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final utterance carry a thin, high-frequency edge, like glass about to shatter under pressure.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "651f13e90679164df3c891120c11327e3b631a77efde858f7f5fe125a5d0bece", "generation_seconds_batch": 31.768644607043825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11932733654975891, "target_z": -0.24609374628090488, "ce": 6.157639026641846, "genuineness": 4.65797233581543, "identity": 0.8172785639762878, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Bitterness/ffe3c165412f0713ee2d504c7fee5399c4e642c71c2f8c6e08a43626894a69a7.mp3" }, { "key": "original-emo_Bitterness-de-0-seed1701-scale0.0", "bucket": "emo_Bitterness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "2d3ae5a1794c70cb2f6c5d79bb09800700b28b356b6a722df089460e02b17975", "task_id": "emo_Bitterness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09071530401706696, "target_z": -0.3164062399870516, "ce": 6.1894097328186035, "genuineness": 4.607763767242432, "identity": 0.3840920925140381, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/de/8a6fbdf9d14dc05eae64da68.mp3" }, { "key": "original-emo_Bitterness-de-0-seed1701-scale0.5", "bucket": "emo_Bitterness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "2489aa3e0699d7220cd15e7a8887222b3a8013b31bcc72059894e62ef62e1580", "task_id": "emo_Bitterness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06528237462043762, "target_z": -0.3789062628737908, "ce": 6.2767791748046875, "genuineness": 4.293961524963379, "identity": 0.4039836823940277, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/de/019b3a0e125d1ce56c7a03db.mp3" }, { "key": "original-emo_Bitterness-de-0-seed1701-scale0.75", "bucket": "emo_Bitterness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "db4511959fea17303129b572cef8f39e1ac116195acca1c8c031ae471d298a1b", "task_id": "emo_Bitterness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3434549570083618, "target_z": 0.30468753375794033, "ce": 6.356205940246582, "genuineness": 4.20609712600708, "identity": 0.42361903190612793, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/de/9054d44e2d86f81335d9e34b.mp3" }, { "key": "original-emo_Bitterness-de-0-seed1701-scale1.0", "bucket": "emo_Bitterness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "a184c8860b2c63fd23989216a5c284109e2eb17ebbbe25b6efc0e17e39effcfa", "task_id": "emo_Bitterness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1074056550860405, "target_z": -0.27539062171003126, "ce": 6.09409761428833, "genuineness": 4.519899368286133, "identity": 0.47166910767555237, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/de/b416902085481ed05cd9e30a.mp3" }, { "key": "original-emo_Bitterness-de-0-seed1702-scale0.0", "bucket": "emo_Bitterness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "652a2fea00db1d42472bb235493257f9a4eb723d1dc69892369cfeac901425f0", "task_id": "emo_Bitterness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10661087185144424, "target_z": -0.2773437577242745, "ce": 6.221180438995361, "genuineness": 4.532451152801514, "identity": 0.5944252014160156, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/de/d8ef896c5196fc2c275502cc.mp3" }, { "key": "original-emo_Bitterness-de-0-seed1702-scale0.5", "bucket": "emo_Bitterness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "85d556dd005cea0c9b16fa72315ddee9ff232fed815d49254a07144a41d896ef", "task_id": "emo_Bitterness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08515185117721558, "target_z": -0.33007811884918886, "ce": 6.23706579208374, "genuineness": 4.632867813110352, "identity": 0.6673372387886047, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/de/e3d5ab94d9fa6781d6a57560.mp3" }, { "key": "original-emo_Bitterness-de-0-seed1702-scale0.75", "bucket": "emo_Bitterness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "a4b45856e16d1c1e37577b9962f48fe44f41250b9c49e825f8282ef13da7523f", "task_id": "emo_Bitterness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11853255331516266, "target_z": -0.24804688229514812, "ce": 6.268836498260498, "genuineness": 4.68307638168335, "identity": 0.7132350206375122, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/de/020c26fc07127abbffb69e79.mp3" }, { "key": "original-emo_Bitterness-de-0-seed1702-scale1.0", "bucket": "emo_Bitterness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "1b3264f70f9297faab90648d8999eeaf4c377bd8d83f0a42d5f4b9c7c7fce373", "task_id": "emo_Bitterness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14078636467456818, "target_z": -0.19335936684659916, "ce": 5.9431867599487305, "genuineness": 4.457139015197754, "identity": 0.6171479225158691, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/de/df5a20e4db03b1cd2c489c67.mp3" }, { "key": "original-emo_Bitterness-de-1-seed1701-scale0.0", "bucket": "emo_Bitterness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "3468290c04f5095546260158a0f106a27e52532e87bc77f98a0ec4b283ca6508", "task_id": "emo_Bitterness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028722554445266724, "target_z": -0.46875000686602175, "ce": 6.395919322967529, "genuineness": 4.607763767242432, "identity": 0.41097956895828247, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/de/8e184bf8bfb03b853a1899b1.mp3" }, { "key": "original-emo_Bitterness-de-1-seed1701-scale0.5", "bucket": "emo_Bitterness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "0c156c7e97d94ad77b54e7b8fd56245d96eedfa279810cffe40f79c045e6c152", "task_id": "emo_Bitterness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009647861123085022, "target_z": -0.5156250148763805, "ce": 6.427689552307129, "genuineness": 4.413206577301025, "identity": 0.5018292665481567, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/de/9c1777912d57f9f70f06578a.mp3" }, { "key": "original-emo_Bitterness-de-1-seed1701-scale0.75", "bucket": "emo_Bitterness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "bb1fc3251a1e00300978d7b4b541863f3752ab85a7d1f1ea249bb2f6e48dec04", "task_id": "emo_Bitterness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05812937021255493, "target_z": -0.3964843771456318, "ce": 6.316492557525635, "genuineness": 4.482243061065674, "identity": 0.3629530072212219, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/de/ddcc89fa031bd412f80745d1.mp3" }, { "key": "original-emo_Bitterness-de-1-seed1701-scale1.0", "bucket": "emo_Bitterness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "f97979905874ac431966edc69b1a694b7c97d2245ea5e891b6320e10c5fd896a", "task_id": "emo_Bitterness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008058309555053711, "target_z": -0.5195312502860843, "ce": 6.427689552307129, "genuineness": 4.111956596374512, "identity": 0.6719880104064941, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/de/e9105d948127fd6a4fd9440e.mp3" }, { "key": "original-emo_Bitterness-de-1-seed1702-scale0.0", "bucket": "emo_Bitterness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "e168d4aa17e90413a79b62ecc6d8dabb380869b13b3dcc222e72ff2e3b5a3945", "task_id": "emo_Bitterness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025543436408042908, "target_z": -0.476562514304212, "ce": 6.403861999511719, "genuineness": 4.375550270080566, "identity": 0.5636845231056213, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/de/7facfbe30d0a1565adae5820.mp3" }, { "key": "original-emo_Bitterness-de-1-seed1702-scale0.5", "bucket": "emo_Bitterness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "68012aa9cfb7b2d5a572749d2f295601ec7ae6fc9640007fc60a5f6d932a62c9", "task_id": "emo_Bitterness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06687194108963013, "target_z": -0.37499999084530433, "ce": 6.221180438995361, "genuineness": 4.419482707977295, "identity": 0.47963234782218933, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/de/3d09d36f7fd76aa86970c196.mp3" }, { "key": "original-emo_Bitterness-de-1-seed1702-scale0.75", "bucket": "emo_Bitterness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "3605d7e2b9cd7c701e4aa81d9523f98f6bd505c8fbe8608b1ffd611f395a3449", "task_id": "emo_Bitterness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017595648765563965, "target_z": -0.49609376459029625, "ce": 6.38003396987915, "genuineness": 4.413206577301025, "identity": 0.44601500034332275, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/de/9f8f1875de958af8974dcb95.mp3" }, { "key": "original-emo_Bitterness-de-1-seed1702-scale1.0", "bucket": "emo_Bitterness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "0272f69c597171e3e92a66946e89edb349f333a80cd5e58cc822462b9b1528fc", "task_id": "emo_Bitterness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021569550037384033, "target_z": -0.4863281211378628, "ce": 6.483288764953613, "genuineness": 4.356721878051758, "identity": 0.5913255214691162, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/de/cff5d79eed6989b85cea6a18.mp3" }, { "key": "original-emo_Bitterness-en-0-seed1701-scale0.0", "bucket": "emo_Bitterness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "603fdc3c0f7c2c60431308a8ea31b430038872a8c1b9cfaa3c9a2af19a1ff10b", "task_id": "emo_Bitterness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035080790519714355, "target_z": -0.4531249919896413, "ce": 6.300607204437256, "genuineness": 4.20609712600708, "identity": 0.3389228582382202, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/en/b8d12233b29f24a2613e1dc5.mp3" }, { "key": "original-emo_Bitterness-en-0-seed1701-scale0.5", "bucket": "emo_Bitterness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "1000cbb3370b79a32beb648a0c45dc80346c53e78b5fb616b481c4f2f8ea7266", "task_id": "emo_Bitterness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05018158257007599, "target_z": -0.41601562743171605, "ce": 6.197352409362793, "genuineness": 4.105680465698242, "identity": 0.30688053369522095, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/en/eb06cb824c8608efcbad2fe2.mp3" }, { "key": "original-emo_Bitterness-en-0-seed1701-scale0.75", "bucket": "emo_Bitterness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "fe4c9a268d7c4d9ed1b42c4b0f8a807d59e9ebe9c989f764b4233b9a98b0b1ea", "task_id": "emo_Bitterness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04382334649562836, "target_z": -0.4316406423080965, "ce": 6.157639026641846, "genuineness": 3.7291181087493896, "identity": 0.3312090039253235, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/en/3522273a5cf0ffe2e9081bba.mp3" }, { "key": "original-emo_Bitterness-en-0-seed1701-scale1.0", "bucket": "emo_Bitterness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "f41fc52112c7e357e412199d4666e94ae7961977a92271ed945eb64969eb8234", "task_id": "emo_Bitterness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05812937021255493, "target_z": -0.3964843771456318, "ce": 6.221180438995361, "genuineness": 4.068024158477783, "identity": 0.34207409620285034, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/en/388cf5738c424d461980bae3.mp3" }, { "key": "original-emo_Bitterness-en-0-seed1702-scale0.0", "bucket": "emo_Bitterness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "27b2e05c80f064c422f6d8de4df62c53e84785fbcb00854e3daad89e5cfdea35", "task_id": "emo_Bitterness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06766670942306519, "target_z": -0.3730468914498438, "ce": 6.125868320465088, "genuineness": 3.8797430992126465, "identity": 0.1600610315799713, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/en/79356c3070d2e2c0eb86fe73.mp3" }, { "key": "original-emo_Bitterness-en-0-seed1702-scale0.5", "bucket": "emo_Bitterness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.5, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "440aa59d3abf931a3790243ceeceacbff8e62afaf5d3056dccb0d35b15678dec", "task_id": "emo_Bitterness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.042233794927597046, "target_z": -0.43554687771780026, "ce": 6.205295085906982, "genuineness": 3.8797430992126465, "identity": 0.28510987758636475, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/en/48b452680831266f7291c18a.mp3" }, { "key": "original-emo_Bitterness-en-0-seed1702-scale0.75", "bucket": "emo_Bitterness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "55c37ae98978661b8196ff36eea04169f4ef97da1da59921f287c437b63a5a37", "task_id": "emo_Bitterness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06846149265766144, "target_z": -0.3710937554356006, "ce": 6.252951145172119, "genuineness": 4.017816066741943, "identity": 0.2871779799461365, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/en/f375be17d94e3ba63f498c9a.mp3" }, { "key": "original-emo_Bitterness-en-0-seed1702-scale1.0", "bucket": "emo_Bitterness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "67f2fb3d804293aa25515cc37faecec9500ffa2dde927f3a4deabaea16d62d2d", "task_id": "emo_Bitterness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08912573754787445, "target_z": -0.32031251201553806, "ce": 6.117925643920898, "genuineness": 4.18099308013916, "identity": 0.3886736333370209, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/en/014f2c793307f40b8c898160.mp3" }, { "key": "original-emo_Bitterness-en-1-seed1701-scale0.0", "bucket": "emo_Bitterness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "a39459dd1a8a46bd86c853ed64742bfebcf675c71df2df682ab8257395d21087", "task_id": "emo_Bitterness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.014195501804351807, "target_z": -0.5742187657346332, "ce": 6.38003396987915, "genuineness": 4.545003414154053, "identity": 0.4374902844429016, "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_Bitterness/en/c7589ad5e870d32870eabbf9.mp3" }, { "key": "original-emo_Bitterness-en-1-seed1701-scale0.5", "bucket": "emo_Bitterness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "97e0f59b952a2ebd5a58dbacf4b1f0e1c95ffe3d98f5a6a8035593f571c23ed7", "task_id": "emo_Bitterness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05393442511558533, "target_z": -0.6718749805462717, "ce": 6.38003396987915, "genuineness": 4.432034492492676, "identity": 0.6126452684402466, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/en/ed04245755bbe671abc2fadc.mp3" }, { "key": "original-emo_Bitterness-en-1-seed1701-scale0.75", "bucket": "emo_Bitterness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "dded378b47e6e53a40bd2cf6940ccf9d680135bfa28b2d5d12eefe8d39f81235", "task_id": "emo_Bitterness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003068596124649048, "target_z": -0.5468750080103587, "ce": 6.435632705688477, "genuineness": 4.243753433227539, "identity": 0.3274252712726593, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/en/20538851133ac1b4fa1573ae.mp3" }, { "key": "original-emo_Bitterness-en-1-seed1701-scale1.0", "bucket": "emo_Bitterness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "91213d10f3a43edd8cc4cbc762c3afec6f3f04c93e2e94bdba57c6e5dcb029a2", "task_id": "emo_Bitterness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05711355805397034, "target_z": -0.6796875246032447, "ce": 6.38003396987915, "genuineness": 4.362998008728027, "identity": 0.2753942310810089, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/en/9f7d1576e0346b85e8ca1952.mp3" }, { "key": "original-emo_Bitterness-en-1-seed1702-scale0.0", "bucket": "emo_Bitterness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "9dbb211bc6eef7bbc8390d4b12e6d6b9cb11a04f6535e44bf2a9e0dac1499a10", "task_id": "emo_Bitterness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.06029266119003296, "target_z": -0.6874999954226522, "ce": 6.268836498260498, "genuineness": 4.482243061065674, "identity": 0.45184943079948425, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/en/a5878b3af13595ad9d7afb5e.mp3" }, { "key": "original-emo_Bitterness-en-1-seed1702-scale0.5", "bucket": "emo_Bitterness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "76681921ce0f255c9f02f9319e291e7c0c145052a3fc3f5d0bb9ad1fbf9653d1", "task_id": "emo_Bitterness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03168061375617981, "target_z": -0.6171874650977227, "ce": 6.395919322967529, "genuineness": 4.3127899169921875, "identity": 0.34142231941223145, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/en/4db5bb96833f24b71ce8e656.mp3" }, { "key": "original-emo_Bitterness-en-1-seed1702-scale0.75", "bucket": "emo_Bitterness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "b8c3a60beaaac80e78cfff455208e97ccfc42be77e37dfa124cd2d9ac9f4943a", "task_id": "emo_Bitterness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0491657555103302, "target_z": -0.6601562376983777, "ce": 6.316492557525635, "genuineness": 4.419482707977295, "identity": 0.3086593747138977, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/en/24c7763b5350bbc43046deeb.mp3" }, { "key": "original-emo_Bitterness-en-1-seed1702-scale1.0", "bucket": "emo_Bitterness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "a4ae152127a67d9271f6a1616896917d7497831191e707dcad267847df8d7357", "task_id": "emo_Bitterness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02214328944683075, "target_z": -0.5937500160207174, "ce": 6.427689552307129, "genuineness": 4.457139015197754, "identity": 0.35119807720184326, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/en/35fccf5b2edea5585ebe34e2.mp3" }, { "key": "original-emo_Bitterness-es-0-seed1701-scale0.0", "bucket": "emo_Bitterness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "f8059d827952f86e54000d65508a13ffcbdaae77a2413b329d26ca9b228ffb30", "task_id": "emo_Bitterness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011237427592277527, "target_z": -0.511718742847894, "ce": 6.006728172302246, "genuineness": 3.948779582977295, "identity": 0.451569139957428, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/es/e8676014b91a6fbebfc639ea.mp3" }, { "key": "original-emo_Bitterness-es-0-seed1701-scale0.5", "bucket": "emo_Bitterness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "11bae22e727f5e52df992b52640c29cb59641d4bbc2f757e616ef057e1170c37", "task_id": "emo_Bitterness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046207696199417114, "target_z": -0.4257812342653668, "ce": 5.974957466125488, "genuineness": 4.256305694580078, "identity": 0.5508722066879272, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/es/bf1fb4fe33eaf53d832b658c.mp3" }, { "key": "original-emo_Bitterness-es-0-seed1701-scale0.75", "bucket": "emo_Bitterness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "46bef6dbe7fd0dc73cdcd697197f5a69904aa65705fbf6083bbbd2827edd74be", "task_id": "emo_Bitterness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016006097197532654, "target_z": -0.5, "ce": 5.855817794799805, "genuineness": 4.030367851257324, "identity": 0.5913829803466797, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/es/6d6b62270d1bad800f496cca.mp3" }, { "key": "original-emo_Bitterness-es-0-seed1701-scale1.0", "bucket": "emo_Bitterness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "e3db86d86c02326c1d860f15d528608e0b6d314a62cd22380af05bd361963595", "task_id": "emo_Bitterness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10661087185144424, "target_z": -0.2773437577242745, "ce": 6.078212261199951, "genuineness": 4.331617832183838, "identity": 0.6736600399017334, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/es/0e3001b54cb68780e327248e.mp3" }, { "key": "original-emo_Bitterness-es-0-seed1702-scale0.0", "bucket": "emo_Bitterness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "6431daf9077f762198a5c5a66533f54fc138c9df619c7395c330e770c113d8d9", "task_id": "emo_Bitterness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11217432469129562, "target_z": -0.2636718788621372, "ce": 6.054384231567383, "genuineness": 4.18726921081543, "identity": 0.7369410991668701, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/es/de845f29d9d28f7541c28a05.mp3" }, { "key": "original-emo_Bitterness-es-0-seed1702-scale0.5", "bucket": "emo_Bitterness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "f5b0c25b9d0295e34cdc27b8c8f3ac4c7c78a6f0fb80939b4b92a70265cfbb46", "task_id": "emo_Bitterness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1089952141046524, "target_z": -0.2714843679909361, "ce": 6.125868320465088, "genuineness": 4.375550270080566, "identity": 0.5967119932174683, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/es/fd8267f6a972f1d42579f9d2.mp3" }, { "key": "original-emo_Bitterness-es-0-seed1702-scale0.75", "bucket": "emo_Bitterness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "8ff4455b1ab53fa421d6932857d26b261c9d21b400e0fe50edac9055ffde4b86", "task_id": "emo_Bitterness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08117794990539551, "target_z": -0.33984376230162233, "ce": 6.0305562019348145, "genuineness": 4.011539936065674, "identity": 0.4552249014377594, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/es/6488e22fdfe92e38b53cb3bb.mp3" }, { "key": "original-emo_Bitterness-es-0-seed1702-scale1.0", "bucket": "emo_Bitterness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "eb4534e3dec64bca8f3e412b5860690d3ac35c3975e56a6951f7c42c121fb2de", "task_id": "emo_Bitterness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04541291296482086, "target_z": -0.42773437027961003, "ce": 6.070269584655762, "genuineness": 3.936227321624756, "identity": 0.47805529832839966, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/es/a886b4d64ce1ee32a1921926.mp3" }, { "key": "original-emo_Bitterness-es-1-seed1701-scale0.0", "bucket": "emo_Bitterness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "10bd850485e364c0c310a6dbc069e03c2454a634b493d0a10a88f5abc9b706fd", "task_id": "emo_Bitterness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028722554445266724, "target_z": -0.46875000686602175, "ce": 6.0146708488464355, "genuineness": 4.532451152801514, "identity": 0.7365196347236633, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/es/ee76e5bd75abb0a29ad9d709.mp3" }, { "key": "original-emo_Bitterness-es-1-seed1701-scale0.5", "bucket": "emo_Bitterness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "f675ce92b8f101d556b9c8586ab212816be336a23090af25bb116857df791287", "task_id": "emo_Bitterness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003068596124649048, "target_z": -0.5468750080103587, "ce": 6.165581703186035, "genuineness": 4.413206577301025, "identity": 0.6276977062225342, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/es/8b2b28d10ffc350180e73868.mp3" }, { "key": "original-emo_Bitterness-es-1-seed1701-scale0.75", "bucket": "emo_Bitterness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "908d0706cd230b967813c3151b32dfc450dbf7fd8a8d8c3b2b820fc8676f0fe4", "task_id": "emo_Bitterness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009647861123085022, "target_z": -0.5156250148763805, "ce": 6.078212261199951, "genuineness": 4.300237655639648, "identity": 0.49464714527130127, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/es/dbf857e53d1a2a5724792d22.mp3" }, { "key": "original-emo_Bitterness-es-1-seed1701-scale1.0", "bucket": "emo_Bitterness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "94f17bb84ad6c41ff996be8a2c33ab1160afb622e264b2d53c02a890717a079d", "task_id": "emo_Bitterness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.015785053372383118, "target_z": -0.578125001144337, "ce": 6.181467056274414, "genuineness": 4.482243061065674, "identity": 0.4704037308692932, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/es/ec35b40a4b66aeacc712c65d.mp3" }, { "key": "original-emo_Bitterness-es-1-seed1702-scale0.0", "bucket": "emo_Bitterness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "3ec81801e78097ab9f39aef932bc2fd6e0e3d68cad365df4699ff2395998e105", "task_id": "emo_Bitterness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008058309555053711, "target_z": -0.5195312502860843, "ce": 6.1020402908325195, "genuineness": 4.369274139404297, "identity": 0.5831382274627686, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/es/08b83e007903c2ecd51beecf.mp3" }, { "key": "original-emo_Bitterness-es-1-seed1702-scale0.5", "bucket": "emo_Bitterness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "474c8003f16d9db2717acd0fde43b403c671b8ce810772bf2782ac737c8875f4", "task_id": "emo_Bitterness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.001479029655456543, "target_z": -0.5429687359818722, "ce": 6.292664527893066, "genuineness": 4.65797233581543, "identity": 0.6505871415138245, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/es/8542f60f98714fcd505159be.mp3" }, { "key": "original-emo_Bitterness-es-1-seed1702-scale0.75", "bucket": "emo_Bitterness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "4daf298db0d792a0118bee4b1c074755aeee2e8ed88f52d42c3b919982b5eeaf", "task_id": "emo_Bitterness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023159101605415344, "target_z": -0.48242188572815903, "ce": 6.078212261199951, "genuineness": 4.7332844734191895, "identity": 0.6478440761566162, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/es/5c906d2bad3298118eaeffa9.mp3" }, { "key": "original-emo_Bitterness-es-1-seed1702-scale1.0", "bucket": "emo_Bitterness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "d1b681a9495e19dded98ce0bb51a7eb6fe36386c01201be4ee15b21ef36dd5c8", "task_id": "emo_Bitterness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00011052191257476807, "target_z": -0.5390625005721685, "ce": 6.1020402908325195, "genuineness": 4.457139015197754, "identity": 0.6568171977996826, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/es/1b876fbab8abeaf538116d53.mp3" }, { "key": "original-emo_Bitterness-fr-0-seed1701-scale0.0", "bucket": "emo_Bitterness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "346ac561a387733248f671863cd41e763f5d3e9e3ae5dcc9babbb3d3bd44ec7a", "task_id": "emo_Bitterness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12568557262420654, "target_z": -0.2304687314045244, "ce": 6.125868320465088, "genuineness": 4.582659721374512, "identity": 0.6110669374465942, "hypothesis": "La porte 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_Bitterness/fr/b28ee6c28db5dec3c69e451d.mp3" }, { "key": "original-emo_Bitterness-fr-0-seed1701-scale0.5", "bucket": "emo_Bitterness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "e7eb756311426eccc83764ac0319a56d92f5e376105db38504e978ae9290c12b", "task_id": "emo_Bitterness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06369282305240631, "target_z": -0.38281249828349456, "ce": 6.157639026641846, "genuineness": 4.331617832183838, "identity": 0.7679462432861328, "hypothesis": "La porte 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_Bitterness/fr/5dcd3911e0ba1d41bc642bca.mp3" }, { "key": "original-emo_Bitterness-fr-0-seed1701-scale0.75", "bucket": "emo_Bitterness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "90e1ccc9bb422dc0589425860d46660301396834843fc73298988904ba03efb5", "task_id": "emo_Bitterness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08912573754787445, "target_z": -0.32031251201553806, "ce": 6.213237762451172, "genuineness": 4.557555198669434, "identity": 0.7404656410217285, "hypothesis": "La porte 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_Bitterness/fr/3807d8d6daa68a1b0099ee90.mp3" }, { "key": "original-emo_Bitterness-fr-0-seed1701-scale1.0", "bucket": "emo_Bitterness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "329e2633c28da339c1313b9565c88bba5cfab048752d7c1e4a86b881aeeb3e10", "task_id": "emo_Bitterness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06687194108963013, "target_z": -0.37499999084530433, "ce": 6.133810997009277, "genuineness": 4.369274139404297, "identity": 0.7625460624694824, "hypothesis": "La porte 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_Bitterness/fr/1126848a70bfc433274aa631.mp3" }, { "key": "original-emo_Bitterness-fr-0-seed1702-scale0.0", "bucket": "emo_Bitterness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "00dac9d6aee560e768ebf0bc0ca7deb95bb5f4efddbe9be3f08fae081bdf0317", "task_id": "emo_Bitterness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08356228470802307, "target_z": -0.33398439087767534, "ce": 6.173524379730225, "genuineness": 4.582659721374512, "identity": 0.7461280822753906, "hypothesis": "La porte 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_Bitterness/fr/95dcc8ba2a923dc676bd7fc7.mp3" }, { "key": "original-emo_Bitterness-fr-0-seed1702-scale0.5", "bucket": "emo_Bitterness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "d2f5e18293c1af80f79968221cade4ac04c9536c6847d7c9e143e6881b6d7d57", "task_id": "emo_Bitterness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03825990855693817, "target_z": -0.44531248455145106, "ce": 6.1894097328186035, "genuineness": 4.369274139404297, "identity": 0.7181378602981567, "hypothesis": "La porte 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_Bitterness/fr/dc7c0a696355114330214cc4.mp3" }, { "key": "original-emo_Bitterness-fr-0-seed1702-scale0.75", "bucket": "emo_Bitterness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "b2b32344137453ba8b100417fba38bd29cb706910e3b3dccb2555e8011c23064", "task_id": "emo_Bitterness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09548397362232208, "target_z": -0.3046874971391576, "ce": 6.062326908111572, "genuineness": 4.6203155517578125, "identity": 0.6504830121994019, "hypothesis": "La porte 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_Bitterness/fr/7fc83ea509e29d19a1ac3c4c.mp3" }, { "key": "original-emo_Bitterness-fr-0-seed1702-scale1.0", "bucket": "emo_Bitterness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "01f31a69dce9a8ac16df0d1b9157ab9415eda1642a7ba538409bfc0cc0654937", "task_id": "emo_Bitterness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08753618597984314, "target_z": -0.3242187474252418, "ce": 6.1894097328186035, "genuineness": 4.218649387359619, "identity": 0.7570204734802246, "hypothesis": "La porte 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_Bitterness/fr/187579f02e0c013b6df44507.mp3" }, { "key": "original-emo_Bitterness-fr-1-seed1701-scale0.0", "bucket": "emo_Bitterness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "a4a177033ad8ba2708c707dd700e40c6ac1cb1476fd17cdede1c60adb1cfc191", "task_id": "emo_Bitterness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07005105912685394, "target_z": -0.3671874834071141, "ce": 6.165581703186035, "genuineness": 4.770940780639648, "identity": 0.7833594083786011, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/fr/383772553caf28393f9934bb.mp3" }, { "key": "original-emo_Bitterness-fr-1-seed1701-scale0.5", "bucket": "emo_Bitterness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "26e8c109704a6ecfaa772c165c41cddf82c8edfdc9e02d7fee98a87e88e43a84", "task_id": "emo_Bitterness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06925627589225769, "target_z": -0.36914061942135734, "ce": 6.221180438995361, "genuineness": 4.557555198669434, "identity": 0.6536827087402344, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/fr/fe050227fe075e97bae3f814.mp3" }, { "key": "original-emo_Bitterness-fr-1-seed1701-scale0.75", "bucket": "emo_Bitterness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "5cdbc101a37217a3e2c30cded57dfb324bed9d87b1e9233d56ab0a9da4ea05b3", "task_id": "emo_Bitterness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009426817297935486, "target_z": -0.5624999862679565, "ce": 6.1894097328186035, "genuineness": 4.6203155517578125, "identity": 0.6094441413879395, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/fr/1b01620dacd91f4d561d12dc.mp3" }, { "key": "original-emo_Bitterness-fr-1-seed1701-scale1.0", "bucket": "emo_Bitterness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "363779762339c2d07661c6cfbf7f6c5b1f4b353a100b94e35bfcac259ce501ef", "task_id": "emo_Bitterness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01997998356819153, "target_z": -0.49023439316634926, "ce": 6.284721851348877, "genuineness": 4.3504462242126465, "identity": 0.6602476835250854, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/fr/2a73f2c74f708a8f4d55cd5f.mp3" }, { "key": "original-emo_Bitterness-fr-1-seed1702-scale0.0", "bucket": "emo_Bitterness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "5fac56f5ed38b636f5039832e8e7951ea1f22d52d4aa9db9e2dbc2989495a7f5", "task_id": "emo_Bitterness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07799884676933289, "target_z": -0.34765623312102983, "ce": 6.181467056274414, "genuineness": 4.65797233581543, "identity": 0.7082972526550293, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/fr/2b82cb9877927f7ea3376fa8.mp3" }, { "key": "original-emo_Bitterness-fr-1-seed1702-scale0.5", "bucket": "emo_Bitterness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "7222d0f25f0036a1d69ca1159f646602602a5d7b7c2def48adba702600e13331", "task_id": "emo_Bitterness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003289639949798584, "target_z": -0.5312499931339782, "ce": 6.141753673553467, "genuineness": 4.18099308013916, "identity": 0.8186683654785156, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/fr/0196cc46ecafac1a2edfbf01.mp3" }, { "key": "original-emo_Bitterness-fr-1-seed1702-scale0.75", "bucket": "emo_Bitterness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "44577bc5de0e3ddf1c60fff00449ec17cb8e6a2394418412fa2e4acefa22ade0", "task_id": "emo_Bitterness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009426817297935486, "target_z": -0.5624999862679565, "ce": 6.252951145172119, "genuineness": 4.293961524963379, "identity": 0.82414311170578, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/fr/f110c3f47c59fef1fcf6fe5a.mp3" }, { "key": "original-emo_Bitterness-fr-1-seed1702-scale1.0", "bucket": "emo_Bitterness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "df344904832c18552cefd2bf6578c123e54ec3f80d3152951b78e0f4f0627feb", "task_id": "emo_Bitterness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0064687579870224, "target_z": -0.523437485695788, "ce": 6.133810997009277, "genuineness": 4.017816066741943, "identity": 0.7126834392547607, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/fr/cc8814d7a562f7bd6a1f2712.mp3" }, { "key": "original-emo_Bitterness-nl-0-seed1701-scale0.0", "bucket": "emo_Bitterness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "40f2d32319a1620b75bb6b642fd8e52c0678bbefbd0c43fa61354c56e12ed62e", "task_id": "emo_Bitterness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1336333453655243, "target_z": -0.21093751773722288, "ce": 6.109982967376709, "genuineness": 4.105680465698242, "identity": 0.4826890528202057, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/nl/323ad48bbfc9b212b2360119.mp3" }, { "key": "original-emo_Bitterness-nl-0-seed1701-scale0.5", "bucket": "emo_Bitterness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "95cc1daa499e72d5c3f34f757c77117a76d454a16fde11a5842f9610dab500d5", "task_id": "emo_Bitterness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13999158143997192, "target_z": -0.1953125028608424, "ce": 6.125868320465088, "genuineness": 4.18726921081543, "identity": 0.5767682194709778, "hypothesis": "De deur 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_Bitterness/nl/c14edb93adecffb09253a3fc.mp3" }, { "key": "original-emo_Bitterness-nl-0-seed1701-scale0.75", "bucket": "emo_Bitterness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "e7ed4ff2495bfef35fe8c8c57f9862b92be469c2144a9d66592fbb973127163c", "task_id": "emo_Bitterness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08674140274524689, "target_z": -0.32617188343948506, "ce": 6.109982967376709, "genuineness": 4.3504462242126465, "identity": 0.562368631362915, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/nl/3b36cb67005c207d7326ae5f.mp3" }, { "key": "original-emo_Bitterness-nl-0-seed1701-scale1.0", "bucket": "emo_Bitterness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "d0eb478ab98e4c07d7d64eeebd0f5d0d5316996efd07fd5637c576798d0dc9cd", "task_id": "emo_Bitterness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07879361510276794, "target_z": -0.3457031337255693, "ce": 6.173524379730225, "genuineness": 4.193545341491699, "identity": 0.6161696910858154, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/nl/3c4e1bb6a538969e5f6e9c0b.mp3" }, { "key": "original-emo_Bitterness-nl-0-seed1702-scale0.0", "bucket": "emo_Bitterness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "e08b87fea90891a9d077c2b5cd18ebec82eb5d6b03dc180ed3c23e68f746e3a0", "task_id": "emo_Bitterness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10263697803020477, "target_z": -0.2871093828673166, "ce": 6.022613525390625, "genuineness": 4.413206577301025, "identity": 0.6884915232658386, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/nl/53979f1c32e6812e8eb064a6.mp3" }, { "key": "original-emo_Bitterness-nl-0-seed1702-scale0.5", "bucket": "emo_Bitterness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "a1f1dc8a4f31574d5d7e107f2e094f425a2cfc3a1296cf520b6506b0165b57e7", "task_id": "emo_Bitterness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06687194108963013, "target_z": -0.37499999084530433, "ce": 6.0305562019348145, "genuineness": 4.256305694580078, "identity": 0.6715024709701538, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/nl/235fc18a3b7331436eef98d3.mp3" }, { "key": "original-emo_Bitterness-nl-0-seed1702-scale0.75", "bucket": "emo_Bitterness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "0c3f3bfa166cf165be5437d594732a29d99f559ba2c3459c412e02df3beb3651", "task_id": "emo_Bitterness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11694300174713135, "target_z": -0.2519531177048519, "ce": 6.0305562019348145, "genuineness": 4.394378662109375, "identity": 0.671585202217102, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/nl/e7e32b3173a56a31dde772d2.mp3" }, { "key": "original-emo_Bitterness-nl-0-seed1702-scale1.0", "bucket": "emo_Bitterness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "f1dfdfb732127fe78a3f44e49f7adae98d47ff3c1b50c54d5ce74e8734ba8913", "task_id": "emo_Bitterness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1264803409576416, "target_z": -0.22851563200906388, "ce": 6.173524379730225, "genuineness": 4.369274139404297, "identity": 0.7435697317123413, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/nl/3b3826729ea985074f097aef.mp3" }, { "key": "original-emo_Bitterness-nl-1-seed1701-scale0.0", "bucket": "emo_Bitterness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "d3dc4aadc4e4205d8db6e5b59f8a96f4b91c64c0d5f59379f14a5ed3a481fd09", "task_id": "emo_Bitterness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07481972873210907, "target_z": -0.35546874055922006, "ce": 6.086154937744141, "genuineness": 4.444586753845215, "identity": 0.6548687219619751, "hypothesis": "Ik 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_Bitterness/nl/8e8ea55b5a49dba8ed5390a7.mp3" }, { "key": "original-emo_Bitterness-nl-1-seed1701-scale0.5", "bucket": "emo_Bitterness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "1aa029da60eeeb5fb92f1d89e20354064f6cb8055bd4f82083e92002e5de8762", "task_id": "emo_Bitterness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13204379379749298, "target_z": -0.21484375314692664, "ce": 6.181467056274414, "genuineness": 4.419482707977295, "identity": 0.8060356974601746, "hypothesis": "ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/nl/b6459bcd3ee1361e0509ec31.mp3" }, { "key": "original-emo_Bitterness-nl-1-seed1701-scale0.75", "bucket": "emo_Bitterness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "e754029c1acce498d7e0ba4e7ccf432468f5f49fe98b3ad4921e2cf2105d02c8", "task_id": "emo_Bitterness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08276751637458801, "target_z": -0.33593749027313585, "ce": 6.09409761428833, "genuineness": 4.080576419830322, "identity": 0.8339684009552002, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/nl/b7c1292c92832289e532d5eb.mp3" }, { "key": "original-emo_Bitterness-nl-1-seed1701-scale1.0", "bucket": "emo_Bitterness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "df42df467574923013666baa7c3de4fac95093b7df6a5007a133f4fb6d997ab5", "task_id": "emo_Bitterness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1352229118347168, "target_z": -0.2070312457087364, "ce": 6.133810997009277, "genuineness": 4.519899368286133, "identity": 0.6476383209228516, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen daar samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/nl/c04e2c426e16a4bd92834d8b.mp3" }, { "key": "original-emo_Bitterness-nl-1-seed1702-scale0.0", "bucket": "emo_Bitterness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "2004fb3a8858d243c6ab6ac02cc115a41ded7bf64531b018bf6ffc2411224015", "task_id": "emo_Bitterness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17098794877529144, "target_z": -0.11914063773074868, "ce": 6.165581703186035, "genuineness": 4.231201171875, "identity": 0.6199854612350464, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/nl/6db132b3561626f30af99ffc.mp3" }, { "key": "original-emo_Bitterness-nl-1-seed1702-scale0.5", "bucket": "emo_Bitterness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "ff4f1e025df90197c6b349bedf5c4924b46e108500523c95778760c734653377", "task_id": "emo_Bitterness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10263697803020477, "target_z": -0.2871093828673166, "ce": 6.165581703186035, "genuineness": 4.2249250411987305, "identity": 0.708193302154541, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/nl/8fd5efa2411492df6b5d9f0e.mp3" }, { "key": "original-emo_Bitterness-nl-1-seed1702-scale0.75", "bucket": "emo_Bitterness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "7deb2c478c0a4145dbdfbdb5f88cb61e2e5d88f77a20d8ddb7160b712c80cf6a", "task_id": "emo_Bitterness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08197273313999176, "target_z": -0.3378906262873791, "ce": 6.157639026641846, "genuineness": 4.432034492492676, "identity": 0.791437029838562, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/nl/25790f9ddd007bcedad22085.mp3" }, { "key": "original-emo_Bitterness-nl-1-seed1702-scale1.0", "bucket": "emo_Bitterness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "d8bf2f6374dc519a22939b010584885b899c3dfbcf97d6dcd0d731756a3a5ba3", "mp3_sha256": "9a619c9ade62cf0b3f9c8de7e12812259edc72c7064c41041016d156180a8cce", "task_id": "emo_Bitterness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Bitterness. 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 Bitterness. 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 Bitterness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10025264322757721, "target_z": -0.2929687542912636, "ce": 6.157639026641846, "genuineness": 4.13078498840332, "identity": 0.6780158877372742, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Bitterness/nl/ecc1c17f661201a70c1adcc4.mp3" } ], "source_standard_audio_unchanged": true }