{ "complete": true, "report": { "bucket": "emo_Fear", "label": "Intense Fear", "definition": { "id": "emo_Fear", "category": "emotion", "head": "emo_Fear", "pole": "high", "label": "Intense Fear", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_fear/full-v2-sealed/sealed-selected", "mission": "emotion_fear", "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": 6.101087222099304, "genuineness": 4.158085498809815, "wer": 0.01627852137327944, "identity": 0.6047011657059193, "voiceclap": 0.06715967996977269, "fitness": 0.6709832938501029, "steering_v2": 0.71540640496587, "raw_target": 1.0428394724428653, "target_cdf": 0.71540640496587, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.130792827606201, "genuineness": 4.147227926254272, "wer": 0.014802138648912843, "identity": 0.6047011657059193, "fitness": 0.6748011894379616, "steering_v2": 0.7200580969878225 }, "none": { "n": 50, "ce": 6.071381616592407, "genuineness": 4.168943071365357, "wer": 0.017754904097646032, "identity": null, "fitness": 0.6671653982622442, "steering_v2": 0.7107547129439176 } } } } ], "selected_wording": { "id": "manual-e2b016e601f8", "general": "Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.", "inline": [ "Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.", "Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.", "End with the sound catching in the throat, a desperate, high-tension release." ], "cfg": 3, "recipe": "P06", "strategy": "local-Gemma-mutation", "timing_syntax": "canonical", "canonical_labels": true, "neutral_event": "keep", "parent": "cfg-3", "origin": "exact_frozen_manual_recipe" }, "selection": { "manual_no_adapter": { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": 0.7661865071191416, "target_raw": 0.7904580973088742, "ce": 6.0150680303573605, "genuineness": 4.32361603975296, "identity": 0.5329813480377197, "wer": 0.014169246646026831, "valid_fraction": 1, "identity_delta": -0.04766434580087662, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 2.9230468690625915, "target_raw": 2.1098986685276033, "ce": 5.737322807312012, "genuineness": 3.9312066197395326, "identity": 0.5390389215201139, "wer": 0.020555555555555556, "valid_fraction": 1, "identity_delta": -0.0416067723184824, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": 0.7661865071191416, "target_raw": 0.7904580973088742, "ce": 6.0150680303573605, "genuineness": 4.32361603975296, "identity": 0.5329813480377197, "wer": 0.014169246646026831, "valid_fraction": 1, "identity_delta": -0.04766434580087662, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": -0.3781005853761104, "target_raw": 0.09045041874051094, "ce": 6.1485049486160275, "genuineness": 4.455255997180939, "identity": 0.6425865143537521, "wer": 0.0058823529411764705, "valid_fraction": 1, "identity_delta": 0.061940820515155794, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": -0.3922485383866189, "target_raw": 0.08179553151130677, "ce": 6.088537788391113, "genuineness": 4.467808055877685, "identity": 0.6034456714987755, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": 0.02279997766017914, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": -0.45849609424478405, "target_raw": 0.041269165277481076, "ce": 6.131031084060669, "genuineness": 4.474711656570435, "identity": 0.5711847502738238, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.009460943564772607, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 3.412890648597393, "target_raw": 2.409556341171265, "ce": 5.728039860725403, "genuineness": 3.876918876171112, "identity": 0.5200935689732432, "wer": 0.095, "valid_fraction": 0.85, "identity_delta": -0.06055212486535311, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 3.022119115790647, "target_raw": 2.170505253970623, "ce": 5.860583066940308, "genuineness": 3.9472105264663697, "identity": 0.49716559424996376, "wer": 0.08916301169590643, "valid_fraction": 0.8, "identity_delta": -0.08348009958863259, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": 1.6271484503643852, "target_raw": 1.3171440795063973, "ce": 5.905558466911316, "genuineness": 4.150868034362793, "identity": 0.5281501611694693, "wer": 0.014454334365325077, "valid_fraction": 1, "identity_delta": -0.05249553266912699, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": 0.24520264210904158, "target_raw": 0.47175074815750123, "ce": 6.082580780982971, "genuineness": 4.3931232452392575, "identity": 0.5809857413172722, "wer": 0.05502558479532164, "valid_fraction": 0.85, "identity_delta": 0.0003400474786758423, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 2.9230468690625915, "target_raw": 2.1098986685276033, "ce": 5.737322807312012, "genuineness": 3.9312066197395326, "identity": 0.5390389215201139, "wer": 0.020555555555555556, "valid_fraction": 1, "identity_delta": -0.0416067723184824, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 2.1352539228062355, "target_raw": 1.6279731839895248, "ce": 5.728834080696106, "genuineness": 4.0005568861961365, "identity": 0.5578752517700195, "wer": 0.027502579979360165, "valid_fraction": 1, "identity_delta": -0.022770442068576813, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 1.9243347106334834, "target_raw": 1.498945190012455, "ce": 5.924720120429993, "genuineness": 4.121998190879822, "identity": 0.5357380315661431, "wer": 0.08651315789473685, "valid_fraction": 0.9, "identity_delta": -0.04490766227245331, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": 1.2722167913372247, "target_raw": 1.100017723441124, "ce": 5.8871910572052, "genuineness": 4.186955285072327, "identity": 0.5745154842734337, "wer": 0.03572733918128655, "valid_fraction": 0.9, "identity_delta": -0.006130209565162659, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 1.196728524435962, "target_raw": 1.0538384325802326, "ce": 5.867532968521118, "genuineness": 4.207666170597077, "identity": 0.5635460704565048, "wer": 0.013157894736842105, "valid_fraction": 0.95, "identity_delta": -0.017099623382091523, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": 0.6188110316880041, "target_raw": 0.7003024317324161, "ce": 5.868922853469849, "genuineness": 4.248460447788238, "identity": 0.5465072795748711, "wer": 0.022485380116959063, "valid_fraction": 0.95, "identity_delta": -0.034138414263725284, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": 0.4328979493567186, "target_raw": 0.5865717202425003, "ce": 5.9966013669967655, "genuineness": 4.315927910804748, "identity": 0.5973619520664215, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": 0.016716258227825166, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": -0.09350585863282393, "target_raw": 0.2645487681031227, "ce": 6.094693374633789, "genuineness": 4.470004737377167, "identity": 0.5747165678068995, "wer": 0.013157894736842105, "valid_fraction": 0.95, "identity_delta": -0.005929126031696796, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": -0.17130127704340392, "target_raw": 0.21695809736847876, "ce": 5.990445780754089, "genuineness": 4.403792452812195, "identity": 0.5391158029437065, "wer": 0.03615067079463364, "valid_fraction": 0.9, "identity_delta": -0.04152989089488983, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": -0.21584472308949662, "target_raw": 0.18970903158187866, "ce": 6.0559728145599365, "genuineness": 4.428269004821777, "identity": 0.579623207449913, "wer": 0.008388157894736842, "valid_fraction": 1, "identity_delta": -0.001022486388683319, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": -0.28074951726128283, "target_raw": 0.15000408813357352, "ce": 6.095686221122742, "genuineness": 4.4091270685195925, "identity": 0.6479070618748665, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": 0.06726136803627014, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": -0.3265624969551751, "target_raw": 0.12197839617729186, "ce": 6.113160085678101, "genuineness": 4.383395326137543, "identity": 0.5554021015763283, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.025243592262268067, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": -0.3801635711596525, "target_raw": 0.08918840512633323, "ce": 6.117131400108337, "genuineness": 4.425131034851074, "identity": 0.5451882690191269, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.03545742481946945, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": -0.3916015618149144, "target_raw": 0.08219131380319596, "ce": 6.120308470726013, "genuineness": 4.420737755298615, "identity": 0.5527832537889481, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.027862440049648284, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": -0.4399902368298901, "target_raw": 0.052589962631464, "ce": 6.138576602935791, "genuineness": 4.3909265995025635, "identity": 0.5487958505749703, "wer": 0.013157894736842105, "valid_fraction": 0.95, "identity_delta": -0.031849843263626096, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": -0.4414062484775876, "target_raw": 0.05172372981905937, "ce": 6.158036160469055, "genuineness": 4.401282024383545, "identity": 0.5679520785808563, "wer": 0.007894736842105263, "valid_fraction": 1, "identity_delta": -0.01269361525774002, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 3.8679687149845137, "target_raw": 2.687946391105652, "ce": 5.441011595726013, "genuineness": 3.632153308391571, "identity": 0.4406680981628597, "wer": 0.07927416580667354, "valid_fraction": 0.8, "identity_delta": -0.13997759567573667, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 3.632031246041728, "target_raw": 2.5436136960983275, "ce": 5.637096261978149, "genuineness": 3.7390029430389404, "identity": 0.4880526950582862, "wer": 0.1710797213622291, "valid_fraction": 0.75, "identity_delta": -0.09259299878031016, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 3.3910156619946226, "target_raw": 2.396174508333206, "ce": 5.636996960639953, "genuineness": 3.7990960121154784, "identity": 0.5255226573906839, "wer": 0.07239400584795322, "valid_fraction": 0.9, "identity_delta": -0.05512303644791246, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 3.3640624920834554, "target_raw": 2.379686141014099, "ce": 5.6267335414886475, "genuineness": 3.80035115480423, "identity": 0.491886830329895, "wer": 0.07297880116959064, "valid_fraction": 0.9, "identity_delta": -0.08875886350870132, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 3.015820301158027, "target_raw": 2.1666520088911057, "ce": 5.637096238136292, "genuineness": 3.863896107673645, "identity": 0.5142443161457777, "wer": 0.08139254385964913, "valid_fraction": 0.75, "identity_delta": -0.06640137769281865, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": 2.370263667707396, "target_raw": 1.771738351881504, "ce": 5.818288397789002, "genuineness": 3.957722842693329, "identity": 0.5100205719470978, "wer": 0.058241959064327484, "valid_fraction": 0.9, "identity_delta": -0.07062512189149857, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": 1.405712878274429, "target_raw": 1.1816827937960626, "ce": 5.920351719856262, "genuineness": 4.190093314647674, "identity": 0.5709057554602623, "wer": 0.06750730994152046, "valid_fraction": 0.85, "identity_delta": -0.009739938378334045, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": 0.5558532690604089, "target_raw": 0.6617885679006577, "ce": 6.007522511482239, "genuineness": 4.364253377914428, "identity": 0.5731904610991478, "wer": 0.04327485380116959, "valid_fraction": 0.8, "identity_delta": -0.0074552327394485475, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": -0.4568359351402607, "target_raw": 0.042284753173589706, "ce": 6.151682019233704, "genuineness": 4.388416171073914, "identity": 0.5806456938385963, "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": -0.4406250024358599, "target_raw": 0.05220165029168129, "ce": 6.179878497123719, "genuineness": 4.400026774406433, "identity": 0.6004938244819641, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.019848130643367767, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": -0.45400390331935603, "target_raw": 0.04401722401380539, "ce": 6.161213231086731, "genuineness": 4.355466949939728, "identity": 0.5926660418510437, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.012020348012447358, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": -0.4640625030448249, "target_raw": 0.037863963097333905, "ce": 6.136988091468811, "genuineness": 4.316241693496704, "identity": 0.510919839143753, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.0697258546948433, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": -0.4402783194047616, "target_raw": 0.05241373062133789, "ce": 6.236827487945557, "genuineness": 4.414838299751282, "identity": 0.5837383687496185, "wer": 0.013804536043666478, "valid_fraction": 0.98, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": 0.5319091768196555, "target_raw": 0.6471409776806831, "ce": 6.034607019424438, "genuineness": 4.191411280632019, "identity": 0.5505273386836051, "wer": 0.019285714285714285, "valid_fraction": 0.98, "identity_delta": -0.033211030066013336, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 2.579218738368769, "target_raw": 1.8995647993683815, "ce": 5.739080114364624, "genuineness": 3.7938241243362425, "identity": 0.5089578618109226, "wer": 0.06010178113267358, "valid_fraction": 0.88, "identity_delta": -0.07478050693869591, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 2.3037573387587402, "target_raw": 1.7310536834597587, "ce": 5.871941156387329, "genuineness": 3.9224829149246214, "identity": 0.5097911757975817, "wer": 0.0367287784679089, "valid_fraction": 0.96, "identity_delta": -0.07394719295203686, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": 0.2754613996100286, "ci95_z": [ -0.19946293770941095, 0.7436352500497889 ], "language_deltas": { "en": 0.8392578431766108, "de": 0.7771483992113271, "fr": -0.5250000389737587, "nl": 0.48536376547306936, "es": -0.19946297083710576 }, "languages_improved": 3, "clear_gain": false, "delta_ce": -0.13286104202270507, "delta_genuineness": -0.1286587905883789, "delta_wer": 0.023373002664764678, "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": 2.0473095615491133, "ci95_z": [ 1.7786035137181784, 2.3160156093800484 ], "language_deltas": { "en": 2.4427734442747355, "de": 2.0666503837551136, "fr": 1.6164062472596576, "nl": 1.7967773451582316, "es": 2.3139403872978286 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.29552690505981444, "delta_genuineness": -0.39758715629577634, "delta_wer": 0.04081606684695929, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 0.9721874962244171, "ci95_z": [ 0.5255468661395596, 1.4278613159723428 ], "language_deltas": { "en": 0.21132811754017902, "de": 1.075146504794357, "fr": 1.7824218605370818, "nl": 0.6174804663522004, "es": 1.1745605318982677 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.20222046852111816, "delta_genuineness": -0.2234270191192627, "delta_wer": 0.005481178242047809, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 2.5, "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain" }, "reference_only": true, "updated": 1793024303.0222328, "example": { "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.", "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." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(End with the sound catching in the throat, a desperate, high-tension release.) [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.", "language": "en", "seed": 1702, "scale": 0.0, "cfg": 2.5, "frames": 128, "reference": true } }, "rows": [ { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "00603b1df201c30e5b0f8c3d502e14c93bbc701488e02eae610e477be0c0bab7", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "478d6449281892d290c6beea4428b5c6c518b776a4c0057030686228897c0ac4", "generation_seconds_batch": 14.470269965007901, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018269121646881104, "target_z": -0.4960937576120622, "ce": 6.109982967376709, "genuineness": 4.582659721374512, "identity": 0.5433372259140015, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/00603b1df201c30e5b0f8c3d502e14c93bbc701488e02eae610e477be0c0bab7.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "006ae25f7cb29ef25479c653a81767c0a09c3b2446a5b31cbfcfc18cec785686", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "8248fabbe03dab05de9fedbf19688ed01e2faa9eb0d3ea0464185af099b4e2b1", "generation_seconds_batch": 20.843444645986892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006321042776107788, "target_z": -0.5156250182689494, "ce": 6.133810997009277, "genuineness": 4.7332844734191895, "identity": 0.5624478459358215, "hypothesis": "J'ai trouvé la 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_Fear/006ae25f7cb29ef25479c653a81767c0a09c3b2446a5b31cbfcfc18cec785686.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "00a8e4121e592546a4fad6fd568a6cad659b4ce14e7f5d3b70b22508def8183e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6227cc064209ba77799578cf6a2e214a312c118a3f155a978e231c8460cb10e0", "generation_seconds_batch": 20.662580291973427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05291852355003357, "target_z": -0.439453145552568, "ce": 6.117925643920898, "genuineness": 4.331617832183838, "identity": 0.39005613327026367, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/00a8e4121e592546a4fad6fd568a6cad659b4ce14e7f5d3b70b22508def8183e.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "017afff928547cc99f3148fe44c6652924484017b2a705ee4c9ada53cf3654a3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "12d9643e594a4ea01fcba8c1e9168913dbf4fb345bd9d36fa44d3add5523bc99", "generation_seconds_batch": 21.03833404404577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04097047448158264, "target_z": -0.4589843574922569, "ce": 6.086154937744141, "genuineness": 4.494794845581055, "identity": 0.7380619645118713, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/017afff928547cc99f3148fe44c6652924484017b2a705ee4c9ada53cf3654a3.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "ee5d315be2d9a11afa5e60593c2bd75d7e071412cdbf7ac88a270b25033130a4", "generation_seconds_batch": 14.290664704982191, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.061282187700271606, "target_z": -0.4257812484775876, "ce": 5.796247482299805, "genuineness": 4.432034492492676, "identity": 0.6697225570678711, "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_Fear/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "0276c5786c3ceeb408634baf12f2de4ae54a674c1c2d43323de9669e39987144", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "881ee67419601d3a772831f625ff04a8a4fdfff2b62883468954eca9990caf6b", "generation_seconds_batch": 21.20726532500703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01707431674003601, "target_z": -0.4980468788060311, "ce": 6.181467056274414, "genuineness": 4.720732688903809, "identity": 0.6652535200119019, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/0276c5786c3ceeb408634baf12f2de4ae54a674c1c2d43323de9669e39987144.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": "0288be085c2eddae1d57265fe75d0a7aaa8e09d44139ae42dd036c45f3ef9da4", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c02854d6644870f0536a4fef477f4ad2323c8af68fe9d89fd1cdb3df8da84671", "generation_seconds_batch": 16.946217847056687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.46273741126060486, "target_z": 0.23046873934311288, "ce": 6.0305562019348145, "genuineness": 3.9550557136535645, "identity": 0.5187779664993286, "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_Fear/0288be085c2eddae1d57265fe75d0a7aaa8e09d44139ae42dd036c45f3ef9da4.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "02912565ff6215f2c19ce000dae43f871a0844f0fb9decf8a892966289212a70", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2d491e80b958e3da664b1254524a31113b6e205dfe28cd2d55f77f6e1bb9c9a3", "generation_seconds_batch": 21.490834222058766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4675166606903076, "target_z": 0.23828127283618666, "ce": 6.070269584655762, "genuineness": 4.105680465698242, "identity": 0.5360699892044067, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/02912565ff6215f2c19ce000dae43f871a0844f0fb9decf8a892966289212a70.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "03199c4d56a3cf6fe1152f3384dc13468c025776df91d8bede4a8f420b0f4a90", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3a81b2dd3526e23606fd2c9bf1fb93b02657bfba1a9ea6abe9c58d51cc3006c2", "generation_seconds_batch": 16.373578864964657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.434169292449951, "target_z": 3.4531248964759538, "ce": 5.895530700683594, "genuineness": 3.9299514293670654, "identity": 0.4071851670742035, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/03199c4d56a3cf6fe1152f3384dc13468c025776df91d8bede4a8f420b0f4a90.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": "0355530424e1cd296756408a1f178e6713a4fc123b7cf68046579463d62dd0bc", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f09db53b6508ace9490d9bdc638cfaa4aedd1db03ced6cb03e731d0c1b9fb8e3", "generation_seconds_batch": 21.663231755956076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11743812263011932, "target_z": -0.333984381850856, "ce": 5.9431867599487305, "genuineness": 3.961331605911255, "identity": 0.47353023290634155, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het naar de lunch terug. Boekenkasten we zetten het naar de lunch terug.", "wer": 0.42857142857142855, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/0355530424e1cd296756408a1f178e6713a4fc123b7cf68046579463d62dd0bc.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "0385e5cf936d3231b45e12018a8f332b33bcf8ad8f5f9d231031ee75d04e6d94", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "efbcedfc3a0697c8694cded5a059073f1ab9fcb8307e851b9bd63a192f5c973b", "generation_seconds_batch": 14.49848424398806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06606140732765198, "target_z": -0.417968763701712, "ce": 6.23706579208374, "genuineness": 4.557555198669434, "identity": 0.644202709197998, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/0385e5cf936d3231b45e12018a8f332b33bcf8ad8f5f9d231031ee75d04e6d94.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "03bdebfdb73352261d99a9e14b95d16521b69b8aece71f4dc773283205bbb97b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2e36bc9d31a4c3fe4734bbc0cbc9f81dc28d59cb2e7bfe2bedf9eb433f3bee15", "generation_seconds_batch": 21.828597442014143, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5248674154281616, "target_z": 0.33203128501548623, "ce": 6.022613525390625, "genuineness": 4.093128204345703, "identity": 0.2951177954673767, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/03bdebfdb73352261d99a9e14b95d16521b69b8aece71f4dc773283205bbb97b.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": "0424832acdfc9b0ee8c97b3c65908ec45cc3375e519f34c87645e734b09a9730", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e70f93e4e45d1db4b21f9b77402fee9087c2dc2a90929735137edda5267f06d8", "generation_seconds_batch": 15.988870390923694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0422725677490234, "target_z": 2.812499975641401, "ce": 5.629451274871826, "genuineness": 3.948779582977295, "identity": 0.6328480839729309, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prolis quand tu partiras !", "wer": 0.08333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/0424832acdfc9b0ee8c97b3c65908ec45cc3375e519f34c87645e734b09a9730.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": "0466b7992b149789c19bc7e96e44c61be5bc6be72d28a59a174b56bf43504f6e", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e4a076f3c2199b7beea36f2ba05975a2fb0d0a04842af6d4c16c106aae97660c", "generation_seconds_batch": 16.547512382967398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5631012320518494, "target_z": 0.3945312606568871, "ce": 6.062326908111572, "genuineness": 3.9299514293670654, "identity": 0.36390218138694763, "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_Fear/0466b7992b149789c19bc7e96e44c61be5bc6be72d28a59a174b56bf43504f6e.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "04a848330d2e6433a01fd23239fae8277fe05fd202aec5bd58bdadf039df2ad0", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4c0343c11f0ee19ddfb84448af849236c1f57fd31c3b626f5cd0f0c5795e177c", "generation_seconds_batch": 22.98661202006042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3922975063323975, "target_z": 1.7500000974343966, "ce": 6.022613525390625, "genuineness": 4.099404335021973, "identity": 0.7251371145248413, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/04a848330d2e6433a01fd23239fae8277fe05fd202aec5bd58bdadf039df2ad0.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": "0559b3265b4de168e6986c931fdc49153c88da67617164a5b5981ab476f434ed", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2429d631e6d1fcb20d7c0d58f419eab66ce5d131f55e2ac94d3e4e2afa275769", "generation_seconds_batch": 15.821734795928933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.85110342502594, "target_z": 2.5, "ce": 5.95112943649292, "genuineness": 3.8922953605651855, "identity": 0.5567806959152222, "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_Fear/0559b3265b4de168e6986c931fdc49153c88da67617164a5b5981ab476f434ed.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "f09051c5f7cd24bf561d4466ac5ff3ed0fca067de801e95a994015bbb1c6e103", "generation_seconds_batch": 15.78217855503317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027827590703964233, "target_z": -0.4804687393431129, "ce": 6.324435234069824, "genuineness": 4.6705241203308105, "identity": 0.6362721920013428, "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_Fear/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "05a66d66e30187bd5b09a93cb586c0eb740de8e3b0b51d2191edf94ebeb1099d", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "567e148c66d9a23aae6c4703d2392efe502e2755e15036748c1caed211bb0993", "generation_seconds_batch": 21.900705031934194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4018022418022156, "target_z": 0.13085936358190667, "ce": 6.09409761428833, "genuineness": 4.256305694580078, "identity": 0.42521756887435913, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/05a66d66e30187bd5b09a93cb586c0eb740de8e3b0b51d2191edf94ebeb1099d.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": "060ce345e74566b5b759655a8c20a2dd881f5a1908d834587cc4dc0f5a74f40e", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "656adf1dbd7cc6daaee414a8735c5b2a125dc96463170925bef23dc3509a45cf", "generation_seconds_batch": 22.416082616895437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9143745303153992, "target_z": 0.9687499634621013, "ce": 5.7684478759765625, "genuineness": 3.923675537109375, "identity": 0.776618242263794, "hypothesis": "Les clés sont sur la taque de la cuisine. J'ai gardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.08333333333333333, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/060ce345e74566b5b759655a8c20a2dd881f5a1908d834587cc4dc0f5a74f40e.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "061a5d70490b243503465e5a9572b67cd861b88dbaf36e767b28f1813c36a9f5", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "25295d2b9633aab6fef38221fe8809fa7dec3a7599e1f46e5d4dc71d9bbb93e8", "generation_seconds_batch": 21.068553318968043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8415449857711792, "target_z": 2.484375030448249, "ce": 5.8875885009765625, "genuineness": 4.231201171875, "identity": 0.5277649760246277, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/061a5d70490b243503465e5a9572b67cd861b88dbaf36e767b28f1813c36a9f5.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "06678f4307e060cf0d3756d4ce8c5057704bce7f1918bbe659ec8bf1651d04eb", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "99e00afa73dc036cd09c24fe45b8ca8e55fa3cc97153df9c4a079975bc8ad981", "generation_seconds_batch": 20.966969914967194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4621400237083435, "target_z": 0.22949220310472757, "ce": 6.062326908111572, "genuineness": 4.356721878051758, "identity": 0.7891736626625061, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/06678f4307e060cf0d3756d4ce8c5057704bce7f1918bbe659ec8bf1651d04eb.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "06f715002cf8d50f81be31adf8619d6acc4a9d7d532e312b5c5ed785ec9c767e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a46698524c20dabab4b7dee807e54ab55b0312b7665fb22cedfd4fb9192f57fd", "generation_seconds_batch": 22.11773615598213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07084065675735474, "target_z": -0.41015623020863823, "ce": 6.260893821716309, "genuineness": 4.65797233581543, "identity": 0.6080036163330078, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/06f715002cf8d50f81be31adf8619d6acc4a9d7d532e312b5c5ed785ec9c767e.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "075b59cb8fdccb570a35740b8e1b114a05118f77d7342684595e5bb3428a4fc2", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "518ccce180876d9f031d3b69773df6158906f3392193b3856762ab8edbf46582", "generation_seconds_batch": 21.647727917996235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2621171474456787, "target_z": 3.171875054806848, "ce": 5.152891159057617, "genuineness": 3.616149425506592, "identity": 0.7060093879699707, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur ta chaise. Dis-moi quand tu prêtes par n'importe quoi qui est pas méquiste que quand tu prêtes.", "wer": 0.7222222222222222, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/075b59cb8fdccb570a35740b8e1b114a05118f77d7342684595e5bb3428a4fc2.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "0786dcfc1af014c497b8ef23cc505d2ce47c0c8ad2e5ac1566dcaf0e3b5eb924", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ce5923e169fca8c369d1eec5ba6ca902f17844354b999f1c1d52fcd3a38d582c", "generation_seconds_batch": 20.183506205910817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1342191696166992, "target_z": 1.328125140061945, "ce": 5.804190158843994, "genuineness": 3.773050308227539, "identity": 0.7261764407157898, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/0786dcfc1af014c497b8ef23cc505d2ce47c0c8ad2e5ac1566dcaf0e3b5eb924.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "07edc10cae42803ab545a618bf2ec5c187a4775e9469caeba0cdd6a5efdc4ad2", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f1d39993548c90886b32634c8aa3adf6be6ee4a3c969ab880345abdcf2a27ea9", "generation_seconds_batch": 16.83027221111115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47826990485191345, "target_z": 0.25585936358190664, "ce": 5.522225379943848, "genuineness": 4.024092197418213, "identity": 0.3989027738571167, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/07edc10cae42803ab545a618bf2ec5c187a4775e9469caeba0cdd6a5efdc4ad2.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "089e091c25cb828f4758e91bf6be94b4fc3536031f3dceed224c1943da0d2544", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b1f21112027f5f4363c3dc5dfe93e93f859c03d5a2069c7577c5ebb2bc306079", "generation_seconds_batch": 16.106028825975955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05172371864318848, "target_z": -0.4414062667465369, "ce": 6.0146708488464355, "genuineness": 4.65797233581543, "identity": 0.5656049251556396, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/089e091c25cb828f4758e91bf6be94b4fc3536031f3dceed224c1943da0d2544.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "08b8c706d90d69a55fe420bbc7f2478e024a6dad64d379d2dec65f55514fd724", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ba31fb8a14a713f7059c18d6b4b866579ac871245e6c4e060b21352d3250ede7", "generation_seconds_batch": 21.900705031934194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09593158960342407, "target_z": -0.36914063641809336, "ce": 5.260117053985596, "genuineness": 4.243753433227539, "identity": 0.4673578143119812, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd.", "wer": 0.3157894736842105, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/08b8c706d90d69a55fe420bbc7f2478e024a6dad64d379d2dec65f55514fd724.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "08dc1c828a8ea6a52978f9f52c8038d13dcb5066f5a61a33ecee1fd86d9e810a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "fd3d48ae3d5d261ece357f0b19e5d5477b102bee21b393d7698017b68b841fc1", "generation_seconds_batch": 23.154282761039212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1856493949890137, "target_z": 3.046874908655253, "ce": 5.760505676269531, "genuineness": 4.306513786315918, "identity": 0.4056510925292969, "hypothesis": "Die Tür 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_Fear/08dc1c828a8ea6a52978f9f52c8038d13dcb5066f5a61a33ecee1fd86d9e810a.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "0920d71ca3192fe45fb267f39d739d315273104ae8ce84dd5e563701aa690ba3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e2cbe24a7ff287790c65c4df32c89c5a1d9b44054e45a28fc344c279712d8621", "generation_seconds_batch": 15.454123741015792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6826891899108887, "target_z": 3.8593748842966544, "ce": 6.086154937744141, "genuineness": 3.6977379322052, "identity": 0.5740927457809448, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/0920d71ca3192fe45fb267f39d739d315273104ae8ce84dd5e563701aa690ba3.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "09369f3a42d20ce97ce8e2d7dcd568e2d6570bbbc689d6b1779d811e1f99871f", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8c09f7c0fe75995cf61e1f34ae58ad36e66fc1338a3c9310039ae982ab402f30", "generation_seconds_batch": 21.147977533051744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08995756506919861, "target_z": -0.3789062423879378, "ce": 5.935244083404541, "genuineness": 4.519899368286133, "identity": 0.63535076379776, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/09369f3a42d20ce97ce8e2d7dcd568e2d6570bbbc689d6b1779d811e1f99871f.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "094086547fd642af630e3604b47e58014ddbf10e597e91bd5e0dd26eff829c51", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "62c619c5c97e0e5229e25bee7d8625b88b7186e3397b5bff3976acb77475a058", "generation_seconds_batch": 16.7651406689547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9981184005737305, "target_z": 4.375000048717198, "ce": 5.502368927001953, "genuineness": 3.810706615447998, "identity": 0.5441202521324158, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/094086547fd642af630e3604b47e58014ddbf10e597e91bd5e0dd26eff829c51.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "0a31d514b7ccd0e0b8b89726f11c99be052df13b688adac6f400673d4902c96f", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2b9dbe71247d8edfb345bceaf8011e9211fe66e92556ada14aecebb83df30bdb", "generation_seconds_batch": 23.165738193085417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1151021718978882, "target_z": 1.2968750060896497, "ce": 6.125868320465088, "genuineness": 4.168440818786621, "identity": 0.31540003418922424, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/0a31d514b7ccd0e0b8b89726f11c99be052df13b688adac6f400673d4902c96f.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "0af0aa1eb7e2494bedc5fa74bf356645e5206dc8568464cb83bb60545cba8a90", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9c516531aa3bc19e09ea9ffc5d61a09e94e32375d622c08a6c006c026997ae30", "generation_seconds_batch": 21.147977533051744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.124660611152649, "target_z": 1.3124999756414009, "ce": 5.748591423034668, "genuineness": 4.457139015197754, "identity": 0.4935547113418579, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/0af0aa1eb7e2494bedc5fa74bf356645e5206dc8568464cb83bb60545cba8a90.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "0b20e3883164b47921d9104bec2bba96b8d93bb341885c7c389affcfba437e77", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4d7496ce90d58c698165304959eda3ecfd1e6a8bef676204a0697e65f4c3acd5", "generation_seconds_batch": 21.80854282702785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0624769926071167, "target_z": -0.4238281272836187, "ce": 6.046441555023193, "genuineness": 3.810706615447998, "identity": 0.5932314395904541, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/0b20e3883164b47921d9104bec2bba96b8d93bb341885c7c389affcfba437e77.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": "0c368e0462697d777414a8cabf7f563e4775dd6d05a526ab8384a9689df3fd07", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d1c21ffec036a1102e9a37a3bdfc25256e65bd2ea0279a113d4616ae9402d465", "generation_seconds_batch": 15.916303651058115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.214324951171875, "target_z": 3.0937502070480924, "ce": 5.450741291046143, "genuineness": 3.8044304847717285, "identity": 0.4717288613319397, "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_Fear/0c368e0462697d777414a8cabf7f563e4775dd6d05a526ab8384a9689df3fd07.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "0c591967a2f6e404d9ee58cfce1bea3bcc665851193688c5e88a9d7736021c80", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7be7256f4af04c8235dd7c4b5cbba8ffcf65d51cdb75d6992283ca7d17232552", "generation_seconds_batch": 23.52511707902886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1508927345275879, "target_z": -0.27929686662673153, "ce": 5.982900142669678, "genuineness": 4.369274139404297, "identity": 0.6069314479827881, "hypothesis": "De tur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/0c591967a2f6e404d9ee58cfce1bea3bcc665851193688c5e88a9d7736021c80.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "57fb5a333ebcf4179d78bbbd4e368300ba22b9acb7f781cb6555a2cb317f4b3f", "generation_seconds_batch": 15.321196867967956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04097047448158264, "target_z": -0.4589843574922569, "ce": 6.133810997009277, "genuineness": 4.300237655639648, "identity": 0.6665774583816528, "hypothesis": "Ik schreef het nummer op de enveloop, lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "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_Fear/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.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": "0cc513e423dfb329871bfc5e0801149c2ec7e6b505687e9b185e604bbb40fec4", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "20c900f29d57328d405f7e21520fdc2f9b2808a0e8cb62c8a76e2e3530a19b5d", "generation_seconds_batch": 16.087857979000546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.093703031539917, "target_z": 4.5312501339722955, "ce": 5.327630043029785, "genuineness": 3.653805732727051, "identity": 0.7471745014190674, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, Lubian, et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "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_Fear/0cc513e423dfb329871bfc5e0801149c2ec7e6b505687e9b185e604bbb40fec4.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "0d89fefc8a56b483687f869d8cac6e6b1a55257b75673c8934c83f4a66a79445", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "726b84c90a1b6f6b116a5589b2620c8f9394fbba9c7b3035e3f52738cffba217", "generation_seconds_batch": 20.391506297979504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5393123626708984, "target_z": 3.6249999512828017, "ce": 5.772419452667236, "genuineness": 3.9801597595214844, "identity": 0.6223829388618469, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/0d89fefc8a56b483687f869d8cac6e6b1a55257b75673c8934c83f4a66a79445.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": "0e1940192a173bd27cb85f45eac0dc3bbd97d6fdaf91c3c248aa914407a82605", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6642aec3484890aff8f4be60939fe81bc05ad749ac1e3dde4006e677099ef9d6", "generation_seconds_batch": 16.4084937160369, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7829457521438599, "target_z": 0.7539062423879378, "ce": 5.609594821929932, "genuineness": 4.18099308013916, "identity": 0.6950714588165283, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue, está la pequeña puerta de madera. Te esperaré al otro lado.", "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_Fear/0e1940192a173bd27cb85f45eac0dc3bbd97d6fdaf91c3c248aa914407a82605.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "0e267c7b07e25d9f1e9eb878ef8789af30c507a4f54cff86755e29180d3791b0", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9de7aae248ef0292bffed6e72ebaae2053e24e50a29cf2e74d9abbc0327de781", "generation_seconds_batch": 21.73516182496678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.443727731704712, "target_z": 3.468749866027705, "ce": 5.657250881195068, "genuineness": 3.7918784618377686, "identity": 0.533383846282959, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/0e267c7b07e25d9f1e9eb878ef8789af30c507a4f54cff86755e29180d3791b0.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "0f9103d8fdd269786e2e64b2dff81bd92595df7acb56da988dbd2e2e826f63ab", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9c48cac2b77f69bd18e5ea7bdfe7bbda8d510c2322b3f8d838bb6fc532acb792", "generation_seconds_batch": 14.52274145197589, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11743812263011932, "target_z": -0.333984381850856, "ce": 6.038498878479004, "genuineness": 4.507347106933594, "identity": 0.7881317138671875, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/0f9103d8fdd269786e2e64b2dff81bd92595df7acb56da988dbd2e2e826f63ab.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "0fc3573121ba5153fc1bd8a4c05ddf416751a5acac5fb62393d154251ac1454d", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "29c1b2ea46e4542a5193d141479d48c5f11ec8ea636de8fb88905ab70f00bac5", "generation_seconds_batch": 14.164195736986585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5117781162261963, "target_z": 1.9453124117000782, "ce": 5.927301406860352, "genuineness": 4.080576419830322, "identity": 0.6016852855682373, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. Vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/0fc3573121ba5153fc1bd8a4c05ddf416751a5acac5fb62393d154251ac1454d.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "0fea1f3cc648d3f43915efce63c9b0d855413f69de22f19cc70de63302b5fd11", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6e6db10f4917cf2200a84f20068718f34f741852e5c23e03987b422c6498f119", "generation_seconds_batch": 22.40661163907498, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9478291273117065, "target_z": 1.0234374543276266, "ce": 5.847874641418457, "genuineness": 3.823258876800537, "identity": 0.5169768333435059, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/0fea1f3cc648d3f43915efce63c9b0d855413f69de22f19cc70de63302b5fd11.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "0ff7a2f42c5238e0d4a58445244a7ab2c9fe25c3118fa048c4ce8339b7a6ff59", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "72e42005b0a3ebb04c7a6fd68b076734a443c057bd0d5879b068f5ca2dcd8390", "generation_seconds_batch": 22.872313371044584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2566331624984741, "target_z": -0.10644532429869645, "ce": 5.935244083404541, "genuineness": 4.595211505889893, "identity": 0.7280153036117554, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/0ff7a2f42c5238e0d4a58445244a7ab2c9fe25c3118fa048c4ce8339b7a6ff59.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "103e45a3e001497c3b177e711c107ac9e143e55cbe45746fe5e5cfbf3b0d5068", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4210ee4313db6b174c1f1d8e4402c1ebb1a99301288eb7870137762afd5daffd", "generation_seconds_batch": 25.35776079900097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1783732920885086, "target_z": -0.23437500608964978, "ce": 6.356205940246582, "genuineness": 4.262581825256348, "identity": 0.7672152519226074, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/103e45a3e001497c3b177e711c107ac9e143e55cbe45746fe5e5cfbf3b0d5068.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "10a466a94483c2de01e998b7ea6febe4b9ea598e3819a04c7cd1b2f8b8f92d5a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4200de5e26c7717f9368e2903d6145168305a0704c89001bd33904418396bfbf", "generation_seconds_batch": 15.851119911996648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18076291680335999, "target_z": -0.23046873934311288, "ce": 6.1894097328186035, "genuineness": 4.15588903427124, "identity": 0.5294572710990906, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/10a466a94483c2de01e998b7ea6febe4b9ea598e3819a04c7cd1b2f8b8f92d5a.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "10e77aa0ec90599313e3b359e5e6ae86a2df22640227518df6592f9ec43f900e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "95010d2ddddabddc35f8a01fc54a7a1a925d12f0dc6de7ff83b2d870ba62fa9a", "generation_seconds_batch": 20.17376328399405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.279931902885437, "target_z": -0.06835938794050578, "ce": 5.8875885009765625, "genuineness": 3.8797430992126465, "identity": 0.43728727102279663, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/10e77aa0ec90599313e3b359e5e6ae86a2df22640227518df6592f9ec43f900e.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": "115805432ef8b5eeb9453488669f081df3b088e1304d4a444dd9f35610d31ceb", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "701be482c020afc9aa771cfac0908f64d746f6631c9de150bb25f38f3e23da74", "generation_seconds_batch": 16.15732797398232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8856991529464722, "target_z": 0.9218749573724515, "ce": 6.284721851348877, "genuineness": 4.557555198669434, "identity": 0.7692577242851257, "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_Fear/115805432ef8b5eeb9453488669f081df3b088e1304d4a444dd9f35610d31ceb.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": "119f37d627f03c982e3386f7d6fa9d3e4174bcca74d0c877046c0af835617b53", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3898a9da011fad8c2738123e09a8df1be58b1f947411967a297d5674c63d776c", "generation_seconds_batch": 26.38773941702675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1485567092895508, "target_z": 1.3515623995207786, "ce": 6.0305562019348145, "genuineness": 3.8797430992126465, "identity": 0.45626604557037354, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/119f37d627f03c982e3386f7d6fa9d3e4174bcca74d0c877046c0af835617b53.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "11f65d463806031f2b8bff3044004ae96ce5cad511b5f27154ce83fdec4ad8b4", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "873979344f55f70a5e23074cf65b4b6691e73ecb742c4dc0d3fe8363972ef9d6", "generation_seconds_batch": 22.698083093971945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6886096000671387, "target_z": 2.2343749330138523, "ce": 5.927301406860352, "genuineness": 4.143336772918701, "identity": 0.3776497542858124, "hypothesis": "I found the little box. It was beside the old window. We can look inside to gigather.", "wer": 0.125, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/11f65d463806031f2b8bff3044004ae96ce5cad511b5f27154ce83fdec4ad8b4.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "11ffd4ed3bdec605c4462a256c5ce069100d917b6ebf9501e81ec651195de213", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5c0302b1e23bcef40f4b66e42dd0ecdd2e050806ac7a321f4440a4298f590b02", "generation_seconds_batch": 22.925258026923984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.395935535430908, "target_z": 3.3906250182689495, "ce": 5.569881439208984, "genuineness": 3.553389072418213, "identity": 0.11621492356061935, "hypothesis": "De de door staat nog open. Ik heb je jas op de op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.21052631578947367, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/11ffd4ed3bdec605c4462a256c5ce069100d917b6ebf9501e81ec651195de213.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": "1264250af184629982d1bce775758966a7d5aae72c16babcfb5b4d22d817e4b2", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e536f32126ea1818ea8bef7a68b8f738b789f9994176ec29c0b15a11f9505296", "generation_seconds_batch": 24.08471425692551, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0338016152381897, "target_z": -0.47070313337326847, "ce": 5.998785495758057, "genuineness": 3.798154592514038, "identity": 0.5877761840820312, "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_Fear/1264250af184629982d1bce775758966a7d5aae72c16babcfb5b4d22d817e4b2.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "126be4e570fb6b01ce20cc439b0e165361b82f78819d98735aece40d541c6949", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a0995ebbe54954d90d9c802df5b89209090e4e872c18c68bf3dd05438bc9c70a", "generation_seconds_batch": 21.181399384047836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03499642014503479, "target_z": -0.46875001217929957, "ce": 5.895530700683594, "genuineness": 4.381826400756836, "identity": 0.703738808631897, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/126be4e570fb6b01ce20cc439b0e165361b82f78819d98735aece40d541c6949.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "127bc223af479cc702469da19ba2b2119003647ab61c48b9d62c40bfdd632ace", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "408213727b92e4817b863743133114dfaee7c0120d5ccd1fc615df9f9de4ed22", "generation_seconds_batch": 22.48659148090519, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02065873146057129, "target_z": -0.49218751522412446, "ce": 5.990842819213867, "genuineness": 4.65797233581543, "identity": 0.6979451179504395, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/127bc223af479cc702469da19ba2b2119003647ab61c48b9d62c40bfdd632ace.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "5b5e860e24a34d94e89335c59aceef3159b67f87af289d70beaf3d285a741192", "generation_seconds_batch": 14.214368503075093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1054900586605072, "target_z": -0.353515618149144, "ce": 6.165581703186035, "genuineness": 4.413206577301025, "identity": 0.744397759437561, "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_Fear/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "12d20e078ce347737d0093db14f5ff49c4c8ab5012e31ce9234590fe53676067", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "444b61895caf8ba0ccd411fb823d66464655ebd045fd3a82888c11afc7a36ae2", "generation_seconds_batch": 21.46742834604811, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6300104260444641, "target_z": 0.5039062423879378, "ce": 5.895530700683594, "genuineness": 4.143336772918701, "identity": 0.6778953671455383, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/12d20e078ce347737d0093db14f5ff49c4c8ab5012e31ce9234590fe53676067.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "13346e28360accb42cb731f9e5bae532a94cab398f4fa2aeef8fc96d761cb42c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "11f789e18346b297295063e7f476941569cd8f87c4110d4b2a6f7cee5848c5a3", "generation_seconds_batch": 21.654425497050397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.64434814453125, "target_z": 0.5273437941499609, "ce": 5.935244083404541, "genuineness": 4.005263805389404, "identity": 0.4480515718460083, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/13346e28360accb42cb731f9e5bae532a94cab398f4fa2aeef8fc96d761cb42c.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": "134f74a705018703f7112eee95db24e941387437f78fe73a1d96401b9b1e0a09", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "27546b91947222efc9b25575a14281e42c5be687c9954054f5c6567dfab86f4a", "generation_seconds_batch": 21.663231755956076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6503758430480957, "target_z": 2.171875054806848, "ce": 6.006728172302246, "genuineness": 3.5722172260284424, "identity": 0.5188175439834595, "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_Fear/134f74a705018703f7112eee95db24e941387437f78fe73a1d96401b9b1e0a09.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "14013a5c5b783e0ddf117bfffaa4752d01de3d65d28d12e598d3455747f10934", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5654d00267daf7cb9fb1659a6e112f339b8813b664bae746cf5deb32f3d02c5e", "generation_seconds_batch": 21.077260173973627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6062216758728027, "target_z": 3.7343751278826454, "ce": 6.308549880981445, "genuineness": 3.923675537109375, "identity": 0.5168746113777161, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/14013a5c5b783e0ddf117bfffaa4752d01de3d65d28d12e598d3455747f10934.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "15089acca981a78b0e431c3826c346940470ba4127ecc554cc6cef6b775d4bcb", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a96c729ab175ee5b040c6289a3e7436625af070bd4e051f01b34450dade5f6c6", "generation_seconds_batch": 17.694362681009807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7400400638580322, "target_z": 3.953125091344747, "ce": 5.6334228515625, "genuineness": 4.042920112609863, "identity": 0.7146927714347839, "hypothesis": "J'ai trouvé j'ai trouvé la petite boîte. Elle était prête. Elle était prête à vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.3684210526315789, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/15089acca981a78b0e431c3826c346940470ba4127ecc554cc6cef6b775d4bcb.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "0753e560a7e7729ea80eb90a737ca512691ee30f65aeb2f9df9702054599e99a", "generation_seconds_batch": 16.755568448919803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018269121646881104, "target_z": -0.4960937576120622, "ce": 6.292664527893066, "genuineness": 4.545003414154053, "identity": 0.641883909702301, "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_Fear/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "1563763c543649d96c47de2f6193d2ee75fd53555845aef031c3f612ebd7e514", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "36dc085282a8802ff44b86f309bc69a4df0d1ee68c20c9ef6849e43513ce9a61", "generation_seconds_batch": 15.762852851999924, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3481433391571045, "target_z": 3.312500170510194, "ce": 5.77639102935791, "genuineness": 3.9801597595214844, "identity": 0.5215224623680115, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/1563763c543649d96c47de2f6193d2ee75fd53555845aef031c3f612ebd7e514.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "15ab0782cb685fa9a83b2076d221d5f21ce0d2c6d7296c1022cc912a07ab7d30", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "de25471a77a744033dca3a42e1b8536ee5d0fe0bd6d0240f384035a9916a7838", "generation_seconds_batch": 20.98483688896522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7375431060791016, "target_z": 0.6796875395827235, "ce": 5.959072113037109, "genuineness": 4.20609712600708, "identity": 0.47747740149497986, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/15ab0782cb685fa9a83b2076d221d5f21ce0d2c6d7296c1022cc912a07ab7d30.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "161c035dce6d4eff87cbcda08a907832b0d702396a81a7a73956118ef9b373e2", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "92e38cae394eda6f94659f488cd92457a51326f6b01e6e0b0da3fea042ca9d4f", "generation_seconds_batch": 22.407891878974624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0481393039226532, "target_z": -0.4472656303284436, "ce": 5.752562999725342, "genuineness": 4.482243061065674, "identity": 0.584586501121521, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/161c035dce6d4eff87cbcda08a907832b0d702396a81a7a73956118ef9b373e2.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": "16463b9631463076b815e523ca557ed50675c48b7e27b931819e9d834c45edf3", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dc65768b83be572a10e7c39bf61e40c88cbcc44abd5fb8b9b92408cae1c0ac98", "generation_seconds_batch": 15.705862830975093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11146408319473267, "target_z": -0.34375001217929957, "ce": 6.348263263702393, "genuineness": 3.911123275756836, "identity": 0.5585106015205383, "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_Fear/16463b9631463076b815e523ca557ed50675c48b7e27b931819e9d834c45edf3.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "16914a86a6806141fa8e3b214fcaada2a804a4bb7c920115b6e2c5d48639861e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "de34c28d7e069bb2882c8de5dcc417f744070a3c93422f1e151c67f1bd68eb7b", "generation_seconds_batch": 22.18869847105816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42510098218917847, "target_z": 0.16894529994009733, "ce": 5.982900142669678, "genuineness": 4.068024158477783, "identity": 0.7781559228897095, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/16914a86a6806141fa8e3b214fcaada2a804a4bb7c920115b6e2c5d48639861e.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": "169bf856615241ef64e595c63d8bfc4a6ee24f2022d0208f7361d85a70051d18", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "332bfe5b84ba5d60388c28fce059789d3fde27e2630f5836d859f04603d9bdaa", "generation_seconds_batch": 16.475885153049603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1706070452928543, "target_z": -0.24707031820904668, "ce": 6.1020402908325195, "genuineness": 4.20609712600708, "identity": 0.5385512113571167, "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_Fear/169bf856615241ef64e595c63d8bfc4a6ee24f2022d0208f7361d85a70051d18.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "171456acdd0ba576f895b8d83c4e2fc393b73e542c9ffb32c8ebbcdc45b924ad", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "732622b6ffc2f06f02960cf9faf4818742ef7dc7cb2500c7ad074bb0220d087c", "generation_seconds_batch": 22.559096329961903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1485567092895508, "target_z": 1.3515623995207786, "ce": 5.34748649597168, "genuineness": 3.9550557136535645, "identity": 0.492168128490448, "hypothesis": "La puerta sigue abierta. Le 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_Fear/171456acdd0ba576f895b8d83c4e2fc393b73e542c9ffb32c8ebbcdc45b924ad.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "17e163d242d345aba6fae7b37916b7ca5cf74180e167fbd24cfb5161214d7c55", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3651a45c5696941aa391ab9520df7951c383054712a9bd64dd6f4d5f3a0c2be2", "generation_seconds_batch": 20.478479165001772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.663572311401367, "target_z": 3.828124945193152, "ce": 5.935244083404541, "genuineness": 3.8797430992126465, "identity": 0.6046701073646545, "hypothesis": "J'ai trouvé la 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_Fear/17e163d242d345aba6fae7b37916b7ca5cf74180e167fbd24cfb5161214d7c55.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "182cb0b3eab396be6f043f3b805749379c04b623f52edfca17acd77b6d4628cd", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "69602aa9bbd5dacd1460337c5d63e8955e4add6c128a50e800a1729de4a19b57", "generation_seconds_batch": 22.407891878974624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10071082413196564, "target_z": -0.3613281272836187, "ce": 5.967014789581299, "genuineness": 4.494794845581055, "identity": 0.5179862976074219, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/182cb0b3eab396be6f043f3b805749379c04b623f52edfca17acd77b6d4628cd.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "18500d06ba0aa89d168e1f9c3c050c9edf3eaf351a70bb1ba440d9d2df61350f", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ff7a272475d4d2c69208b7165bdf8caa0b24af12481cc806ab29a5e4469195b6", "generation_seconds_batch": 15.796172596979886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6634650230407715, "target_z": 0.5585937332534631, "ce": 6.0146708488464355, "genuineness": 4.469690799713135, "identity": 0.6975598335266113, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/18500d06ba0aa89d168e1f9c3c050c9edf3eaf351a70bb1ba440d9d2df61350f.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": "1881f92a1da86930e8028ace6da1d65e49002532f887e60b9f35c487b890174c", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e47a9266149720162adda2df64943772bc8d06ecc47db4870101035ac9e6311e", "generation_seconds_batch": 22.859467306057923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.787832260131836, "target_z": 4.031249939103502, "ce": 5.7406487464904785, "genuineness": 3.613011360168457, "identity": -0.11555572599172592, "hypothesis": "De sleutels liggen op de keukentafel. Ik... ik keek in de laag en daarna naast het gaan. Neem ze mee als je weggaat.", "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_Fear/1881f92a1da86930e8028ace6da1d65e49002532f887e60b9f35c487b890174c.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "18da760627a0b638bf06100ebec53bbf7a91dcef78fdc15ea78d65359e93812e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6f03aed96988169a3f203a7ae274d191e1aa40fae81a813de185748a2650ba2f", "generation_seconds_batch": 22.393934487947263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.793752670288086, "target_z": 2.4062499878207007, "ce": 4.956310272216797, "genuineness": 3.9173994064331055, "identity": 0.3520945906639099, "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_Fear/18da760627a0b638bf06100ebec53bbf7a91dcef78fdc15ea78d65359e93812e.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "18faef87c949b34572f7de53dbb03c0b18fecffa275f61e2092c33a7b76a9362", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f903528818aae4dc6a9a37616afead064b0d7dd3a4f837a36bb5199db53a96c9", "generation_seconds_batch": 22.002953468007036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003237396478652954, "target_z": -0.5312499878207004, "ce": 6.300607204437256, "genuineness": 4.457139015197754, "identity": 0.38361889123916626, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/18faef87c949b34572f7de53dbb03c0b18fecffa275f61e2092c33a7b76a9362.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "190beedd2d575ce1709b7b26bc1eb3325dfacd74348747a64e164c3ebbdebad3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "071ffcc401cb915d0c3778b81fab0298c588d0e659ad030b6666889430c87e70", "generation_seconds_batch": 25.474248272017576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05172371864318848, "target_z": -0.4414062667465369, "ce": 6.038498878479004, "genuineness": 4.482243061065674, "identity": 0.7159020900726318, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/190beedd2d575ce1709b7b26bc1eb3325dfacd74348747a64e164c3ebbdebad3.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "1922bf10c403f4a2817ec9e3a30c4651c7354f8d01b43084c6666e9d80f1ccf5", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ad9f3145e000170d3f35c1eacf453b6d83c31952165476c5aba5265f690273af", "generation_seconds_batch": 21.495653947000392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025437980890274048, "target_z": -0.48437498173105065, "ce": 6.284721851348877, "genuineness": 4.7332844734191895, "identity": 0.5681993961334229, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/1922bf10c403f4a2817ec9e3a30c4651c7354f8d01b43084c6666e9d80f1ccf5.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "192c8810dc8a0cbbee854fc86751db89fda0e5fe5c90a2bad5adc737f5c13909", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e9f3e81e046315d40a6d6595f2648ad291d8928d3adcd8357727977a587a49f5", "generation_seconds_batch": 20.496791540062986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8834168910980225, "target_z": 4.187500024358599, "ce": 5.788304805755615, "genuineness": 3.9048471450805664, "identity": 0.7588530778884888, "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_Fear/192c8810dc8a0cbbee854fc86751db89fda0e5fe5c90a2bad5adc737f5c13909.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "19771fbd43ca6f92753f473887663121c3df9cb6d213537f25365df06cd3dbb6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ee144ae3bdb2384db5fc06f98caee55f8acc7fdb466cbd832d4f50f63f4f5864", "generation_seconds_batch": 22.10605249798391, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1198813915252686, "target_z": 1.3046874908655253, "ce": 6.109982967376709, "genuineness": 4.6705241203308105, "identity": 0.6519935131072998, "hypothesis": "Ich habe die kleine Schartel 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_Fear/19771fbd43ca6f92753f473887663121c3df9cb6d213537f25365df06cd3dbb6.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "1989cf5964af896b8f7d7f8f32b9c5e63d4a8ef06c11c2477c438f3c2ee2d9d3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2ca77eddb9ed6469dac9b617ccbce71c42e72a0cae873b97746937b630adf6fd", "generation_seconds_batch": 20.035916161024943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8187899589538574, "target_z": 0.8124999756414009, "ce": 5.95112943649292, "genuineness": 4.758388519287109, "identity": 0.7493476867675781, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/1989cf5964af896b8f7d7f8f32b9c5e63d4a8ef06c11c2477c438f3c2ee2d9d3.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "19eabf28303c70a32db7164b782a3930310ef163bf9920ea795755dcec570556", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7fbb15d616c3a5970a062ec6047d8c45d21d82f059951ce45416eecae3b7845a", "generation_seconds_batch": 21.485096354037523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.548870801925659, "target_z": 3.640624920834553, "ce": 5.331601142883301, "genuineness": 3.6067352294921875, "identity": 0.09591718018054962, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/19eabf28303c70a32db7164b782a3930310ef163bf9920ea795755dcec570556.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": "19f6ccd1a86846229cb96fe7c60d8289e560601600136f167323beaa1c29fada", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d49097eea1badf261b8e4b57f1b2f1a305f016f30b6d7d909ef0d4d4cd94f6d3", "generation_seconds_batch": 20.509978918009438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5739080905914307, "target_z": 2.046874908655253, "ce": 5.486483573913574, "genuineness": 4.118232727050781, "identity": 0.6660029888153076, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lubien. Et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "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_Fear/19f6ccd1a86846229cb96fe7c60d8289e560601600136f167323beaa1c29fada.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "1a15dd640eab176ad9cb0f77b354fa9d42529d6e6e3ba244652531fc6c8f7ca8", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a52700c3507d2d48864bd45669320c6fea8ca37be376a0a3fd20001a631e799f", "generation_seconds_batch": 22.405851930961944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6921404004096985, "target_z": 0.6054687393431128, "ce": 5.752562999725342, "genuineness": 4.281409740447998, "identity": 0.5199588537216187, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/1a15dd640eab176ad9cb0f77b354fa9d42529d6e6e3ba244652531fc6c8f7ca8.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "1a1724552a84a634e23adf30e2144d809a8d0455ef3f1d9a870bb331ed221d40", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "56359771808a26797b7c94e3b4923ea8833ad29c512340f3ca28e32f9a421e4b", "generation_seconds_batch": 16.654756297008134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.679051160812378, "target_z": 2.2187499634621015, "ce": 5.80021858215332, "genuineness": 4.369274139404297, "identity": 0.539665937423706, "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_Fear/1a1724552a84a634e23adf30e2144d809a8d0455ef3f1d9a870bb331ed221d40.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "1a1b564d519fc7b601a88fac74c268c726519a30c77a74d9024ba184d8c76f07", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "72484c83e5f991c83a5ef4770d5bbd920b54dc5cb01a43dade1dcfbcfc6f7533", "generation_seconds_batch": 16.370319727924652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.037386029958724976, "target_z": -0.46484376979136177, "ce": 6.1894097328186035, "genuineness": 4.494794845581055, "identity": 0.2805095613002777, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/1a1b564d519fc7b601a88fac74c268c726519a30c77a74d9024ba184d8c76f07.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "1a45f45208a2648a015ea9ec563087f1a2411c8d3238d231e8da38460d5807cb", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b9d8114a40f356fe007fe46cecca7788e20b8009b238bcf96eea7972daf5ab5e", "generation_seconds_batch": 22.411851519951597, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2213863581418991, "target_z": -0.1640624969551751, "ce": 6.197352409362793, "genuineness": 4.369274139404297, "identity": 0.5199102163314819, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/1a45f45208a2648a015ea9ec563087f1a2411c8d3238d231e8da38460d5807cb.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "1a5f6078a3a078b1c2ffa4f9d4e66f350ca00d829f724860d1895b9449b8ea48", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "18e6effd077a620205f47f76c97695beb0112e6316a4b3fa9db072527d4fc861", "generation_seconds_batch": 16.081018986995332, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06606140732765198, "target_z": -0.417968763701712, "ce": 6.340320587158203, "genuineness": 4.218649387359619, "identity": 0.6968553066253662, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/1a5f6078a3a078b1c2ffa4f9d4e66f350ca00d829f724860d1895b9449b8ea48.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "1a9b45299d4ba0085a7db0edd3f0745faaba0db3eb30ec9b9fbd7bae4342b607", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "78d32269e3cfb8fb10cb7a4ef66cd44c3b3a268ae25c0db54efd8e2b7524ae93", "generation_seconds_batch": 20.906569999991916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0338016152381897, "target_z": -0.47070313337326847, "ce": 6.157639026641846, "genuineness": 4.519899368286133, "identity": 0.7100557684898376, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/1a9b45299d4ba0085a7db0edd3f0745faaba0db3eb30ec9b9fbd7bae4342b607.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "1ab22bfc39b8ca111eb0183c12b5f7c36aa8ec68498230b1b24daeb514a7219b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b72bfd748f8fee176ea75a92f330fc5e5ddc4e4de88c1974ba8009637dae2680", "generation_seconds_batch": 21.459582892013714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.037386029958724976, "target_z": -0.46484376979136177, "ce": 6.062326908111572, "genuineness": 4.507347106933594, "identity": 0.4436374604701996, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/1ab22bfc39b8ca111eb0183c12b5f7c36aa8ec68498230b1b24daeb514a7219b.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "1bdc231b04b15b3122dddc46f15fce24625157f4fd14ff3ac7b511d7c81043b0", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6be2e5a80faa2f223bda5988e7a9f786da4f6fbc21dd9715d48b433116e27f60", "generation_seconds_batch": 21.964428964070976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3804566860198975, "target_z": 5.0, "ce": 5.148920059204102, "genuineness": 3.405902147293091, "identity": 0.38829654455184937, "hypothesis": "The 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_Fear/1bdc231b04b15b3122dddc46f15fce24625157f4fd14ff3ac7b511d7c81043b0.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "1bfc36951ff2e4beb5285389336c0c889f92cc9d64543aedaf446649cb3338ba", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3ac2fd5f157b95705535cfa1e0eaf747769a140c296a8057e9075fa948168a44", "generation_seconds_batch": 15.694013391970657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44839972257614136, "target_z": 0.207031236298288, "ce": 5.839932441711426, "genuineness": 4.557555198669434, "identity": 0.5489096641540527, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/1bfc36951ff2e4beb5285389336c0c889f92cc9d64543aedaf446649cb3338ba.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "1c0f63748a5987557738dd06fb3f55d9269f27d89e352c23f7629bb1daf2f5e3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "77be6f69b0bea176923de31e30326d6e462b47137af91d5edcddda7a5e7338a6", "generation_seconds_batch": 21.181399384047836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5451791286468506, "target_z": 0.36523439403015556, "ce": 5.8875885009765625, "genuineness": 4.331617832183838, "identity": 0.673474907875061, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/1c0f63748a5987557738dd06fb3f55d9269f27d89e352c23f7629bb1daf2f5e3.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "1c4b91f7436ca2869a2352aacda3d32b75067132ef941c3a7e7b1aed91460860", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e86c4d9479854cbfafe251d54459031a62ae75fe3822d6629b75c8f72b2838fd", "generation_seconds_batch": 22.04899805295281, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008710682392120361, "target_z": -0.5117187271638133, "ce": 6.340320587158203, "genuineness": 4.507347106933594, "identity": 0.41757529973983765, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/1c4b91f7436ca2869a2352aacda3d32b75067132ef941c3a7e7b1aed91460860.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "1c8212c37a60594f422d2823ce452b77d40476c34bb9165e594a5d4241524037", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0e7cb0ba20d2384ab4d93a9efb05e1a023135e3f84f2b852db46e8bf6968e5f4", "generation_seconds_batch": 23.590407209005207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011100292205810547, "target_z": -0.5078124847758756, "ce": 6.348263263702393, "genuineness": 4.268857479095459, "identity": 0.462347149848938, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/1c8212c37a60594f422d2823ce452b77d40476c34bb9165e594a5d4241524037.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "1d50bc9a84e02bdea04fec9e02d8abd5f368e2237091d05263c0b9ba40cd1771", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ed519e7c74d9eb6c82a693a8d487a24afb2031b410f76245034f89fc614f9ada", "generation_seconds_batch": 20.523497524904087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03141200542449951, "target_z": -0.4746093757612062, "ce": 6.086154937744141, "genuineness": 4.105680465698242, "identity": 0.6508504152297974, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/1d50bc9a84e02bdea04fec9e02d8abd5f368e2237091d05263c0b9ba40cd1771.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "ca09d3b88914f9836ee84b66bdaf201d3edb47d8ee22f37e1a36e36f98553e2b", "generation_seconds_batch": 15.9567910740152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07084065675735474, "target_z": -0.41015623020863823, "ce": 6.252951145172119, "genuineness": 4.344170093536377, "identity": 0.6567760109901428, "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_Fear/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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "7d1d690acd13e2c90e04c4c9a19199dfb96a4541492fe80b1ddba37ce4255c99", "generation_seconds_batch": 15.909556800033897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013489902019500732, "target_z": -0.5039062423879378, "ce": 6.340320587158203, "genuineness": 4.394378662109375, "identity": 0.3677077293395996, "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_Fear/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "1e0d23146acbcce5c9075b8252d46d7905200ea6124ac2e2d508bfef3827a2a0", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "916a5f4edb585af8f0abbac2138d1ed2f6f00688676d7562a8d985434f15aa8d", "generation_seconds_batch": 15.818316248012707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06845101714134216, "target_z": -0.41406252131377425, "ce": 6.141753673553467, "genuineness": 4.65797233581543, "identity": 0.6218224763870239, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/1e0d23146acbcce5c9075b8252d46d7905200ea6124ac2e2d508bfef3827a2a0.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "ea76e7ede7e47957bc9784f1439f8b357fc41961941e45f62ddcedf56942be2b", "generation_seconds_batch": 15.9567910740152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.061282187700271606, "target_z": -0.4257812484775876, "ce": 6.332377910614014, "genuineness": 4.231201171875, "identity": 0.6515820622444153, "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_Fear/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "1f0b2724cc83c9ac437cfbca50cb217e026a17bf3c306dd0de3c0cf3d2ae1517", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "63098ccb067aaf0e50a8ba862fe27639589f23df3eabd64102cf7cc19ee39ef5", "generation_seconds_batch": 14.236496362020262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21123048663139343, "target_z": -0.18066407582110888, "ce": 6.197352409362793, "genuineness": 4.720732688903809, "identity": 0.7462834119796753, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/1f0b2724cc83c9ac437cfbca50cb217e026a17bf3c306dd0de3c0cf3d2ae1517.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "1f468cc20154d7e7f420a0cf7fdf08125b17297b4dd7b41c7c5d189ea658e3b4", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3fe5d4c253602434cc7a7d38cf8985cc1f25abdf5eb34a22e901435019c694a2", "generation_seconds_batch": 21.651122921030037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06486660242080688, "target_z": -0.4199218848956809, "ce": 5.911416053771973, "genuineness": 4.570107460021973, "identity": 0.5526475310325623, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/1f468cc20154d7e7f420a0cf7fdf08125b17297b4dd7b41c7c5d189ea658e3b4.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "1f9758bd8f00c28408696f6c2d282fc67f987afcaaf32268f95cd3616469456a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5980cb766d7d78d8d89fc290323f206257f1c92e61e2a03b8572f1b5910b17d1", "generation_seconds_batch": 22.95254271000158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4878820180892944, "target_z": 1.9062499878207004, "ce": 5.911416053771973, "genuineness": 4.243753433227539, "identity": 0.6599488258361816, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Mantel auf den Stuhl gelegt. 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_Fear/1f9758bd8f00c28408696f6c2d282fc67f987afcaaf32268f95cd3616469456a.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": "1fb8ce7652087e1130c5bac01d79cafe7743d19d42bc8918e79ed8fd45c2b3c3", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4a580e764da534089dcd2808a49900bdd8d15836a86a75f969e6cd2a3d2e5f02", "generation_seconds_batch": 16.52821892197244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4280880093574524, "target_z": 0.17382812728361866, "ce": 6.078212261199951, "genuineness": 4.13078498840332, "identity": 0.5693027377128601, "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_Fear/1fb8ce7652087e1130c5bac01d79cafe7743d19d42bc8918e79ed8fd45c2b3c3.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "2002d584d2e5de0b6a904e3f3e0bdc4cbf4a252020fb63d2ed91b4612b97ba05", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e71ea457af317301a341f518bdbf89f62b6af9c3074c34a838edd406ade6a81d", "generation_seconds_batch": 24.66057071101386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06486660242080688, "target_z": -0.4199218848956809, "ce": 6.2767791748046875, "genuineness": 4.607763767242432, "identity": 0.5536070466041565, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2002d584d2e5de0b6a904e3f3e0bdc4cbf4a252020fb63d2ed91b4612b97ba05.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "2089b88f7496e4277cbff74bf6170e2ee4659e3dda713e6fa9739068bd09eac6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ba43e0ffa5c20e43cb70b38c72da42714631b8f16b540e1c90d32d3a6a3384f1", "generation_seconds_batch": 20.887526395963505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1496979296207428, "target_z": -0.28124998782070043, "ce": 6.213237762451172, "genuineness": 4.356721878051758, "identity": 0.6146106719970703, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2089b88f7496e4277cbff74bf6170e2ee4659e3dda713e6fa9739068bd09eac6.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "2090795f0892824296ae097451c30fb4326c3c26f47b7cfafb0dbf99328c4fe2", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3873916420b740e7094b011aa53cf5aa543ce07a0af1cd8eff3748d187de1962", "generation_seconds_batch": 15.267978359013796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023048341274261475, "target_z": -0.48828127283618666, "ce": 6.070269584655762, "genuineness": 3.7040140628814697, "identity": 0.41311115026474, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2090795f0892824296ae097451c30fb4326c3c26f47b7cfafb0dbf99328c4fe2.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": "20d3eccac94152c26149efee1e63e4a8986ca0123bd8ba05525a6dee7f0436e2", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0cf56ec549aeb000781155e6403e94019b5f1c95f504069d71e26fa2df696167", "generation_seconds_batch": 15.930342082981952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3328021168708801, "target_z": 0.018066383223511777, "ce": 6.1894097328186035, "genuineness": 4.042920112609863, "identity": 0.6328093409538269, "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_Fear/20d3eccac94152c26149efee1e63e4a8986ca0123bd8ba05525a6dee7f0436e2.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": "2201e60868772a5dd1dd5f735a81579a1b39b905277b9b025e9f2ecbd0d2bd81", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "dd3ea5ca9360c632a52468b8e3e8f8745c2d2d7978ce31f7104af252c11f23c7", "generation_seconds_batch": 21.57515984098427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4628448486328125, "target_z": 3.500000194868793, "ce": 5.895530700683594, "genuineness": 3.835810661315918, "identity": 0.5486438274383545, "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_Fear/2201e60868772a5dd1dd5f735a81579a1b39b905277b9b025e9f2ecbd0d2bd81.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": "223530bfbd336b8a4eb31a92ec25acdff16a9017269662d3b1dc88bf6f196c22", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "00fe23bf3faed5ba32b6310fe7028cf5396b96e899d3fad42963ffdd63cbac59", "generation_seconds_batch": 22.353764098952524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8988957405090332, "target_z": 2.5781250426275486, "ce": 5.911416053771973, "genuineness": 3.8922953605651855, "identity": 0.11325141787528992, "hypothesis": "Je bricht, kom nadat ik vertrokken was. Ik las het toe hier en legde mijn telefoon weg. Zeg maar van even kunnen praten.", "wer": 0.2608695652173913, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/223530bfbd336b8a4eb31a92ec25acdff16a9017269662d3b1dc88bf6f196c22.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "223e5b39054311d9e7c8ae35494e23f8bd087814eb54b60b76a90fd7bb29d347", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c4e755d103ba38bab0ba18583147cfb78730c252ddffbaed301a43db494abcc0", "generation_seconds_batch": 15.331929822918028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31980860233306885, "target_z": -0.003173828029849222, "ce": 6.0146708488464355, "genuineness": 4.457139015197754, "identity": 0.46301960945129395, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/223e5b39054311d9e7c8ae35494e23f8bd087814eb54b60b76a90fd7bb29d347.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "22748df7e7873acf911b444e5a3ff7c8c09429408eb32399c465120b9aa8f648", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "51580844a4cf026e33cfdcd169149d08df75000c125884c38083fdee19f34481", "generation_seconds_batch": 14.236496362020262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8952576518058777, "target_z": 0.9375000243585991, "ce": 5.8875885009765625, "genuineness": 4.519899368286133, "identity": 0.7666406631469727, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/22748df7e7873acf911b444e5a3ff7c8c09429408eb32399c465120b9aa8f648.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "22cfa991eee17c3e4b6d2c54d590950e55318fa9270732a6e110539d2b05428e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "cd917cc8dc8eed49ec2f636bb4002db9b7056de387e60a11e4467ca968d4400a", "generation_seconds_batch": 15.295291983056813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8893373012542725, "target_z": 2.5625000730757974, "ce": 6.0146708488464355, "genuineness": 4.256305694580078, "identity": 0.7765257358551025, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt, Tima, mes ormes. Dis-moi quand tu es prêt.", "wer": 0.5, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/22cfa991eee17c3e4b6d2c54d590950e55318fa9270732a6e110539d2b05428e.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "2370166146aad665006d87dc371e005aefa0c4561c9319e5fc1571b0e58e8e17", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e43d5f2fe2e23e7e348533355db302cfeef9a585742b396356000900b514b1c4", "generation_seconds_batch": 21.023496010922827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3099093437194824, "target_z": 3.2499999025656034, "ce": 5.1926045417785645, "genuineness": 3.8169827461242676, "identity": 0.39852720499038696, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime, ¿cuándo estás listo?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2370166146aad665006d87dc371e005aefa0c4561c9319e5fc1571b0e58e8e17.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": "23c8bc2029e7dcafdda3e6ada6da4fb221aae31c3e87e74971249bb4e3e6e87d", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dfd8fa28ede95e5c6efd6a882b40df9d3bfa7d34135cea472ec4db0c62573b2b", "generation_seconds_batch": 18.40502792899497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3039889335632324, "target_z": 4.874999853848405, "ce": 5.935244083404541, "genuineness": 3.9048471450805664, "identity": 0.6302605867385864, "hypothesis": "Haz llave. Se están en la mesa de la cocina. Miré en el cajón. Y luego, junto a la ventana, llévatelas cuando te vayas.", "wer": 0.13043478260869565, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/23c8bc2029e7dcafdda3e6ada6da4fb221aae31c3e87e74971249bb4e3e6e87d.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": "240ee57572e80657305472868bb0fd710310e9f44ebd5793a81610900e1e288c", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8bb5c865fb247da17d3159fd2429b1325f1ad26ab8748ef8bf9656c023528877", "generation_seconds_batch": 15.641704804031178, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24169808626174927, "target_z": -0.13085936358190667, "ce": 6.165581703186035, "genuineness": 4.519899368286133, "identity": 0.4119667410850525, "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_Fear/240ee57572e80657305472868bb0fd710310e9f44ebd5793a81610900e1e288c.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "24ca5c4ac0edaa80ee2f78bce141ed90c7e081ebd00e698368cbf1850c657f4d", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cebaf7b4d1b28ff1bea216be103f3936792df3565959b874fcbf16587eb88a3e", "generation_seconds_batch": 20.908118318999186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5320362448692322, "target_z": 0.34375001217929957, "ce": 5.816103935241699, "genuineness": 4.432034492492676, "identity": 0.5206907391548157, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. Vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/24ca5c4ac0edaa80ee2f78bce141ed90c7e081ebd00e698368cbf1850c657f4d.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "24ff8fa7526f59c7c9ae53f428e5bbc70318ef18c1e4823e468eef2efc412764", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8431cf2f91e08c56d0e4554cfef981a8c753309a64a55873a4155774ec84e075", "generation_seconds_batch": 15.425279182032682, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18195772171020508, "target_z": -0.228515618149144, "ce": 6.221180438995361, "genuineness": 4.796044826507568, "identity": 0.7471228837966919, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/24ff8fa7526f59c7c9ae53f428e5bbc70318ef18c1e4823e468eef2efc412764.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": "251c97ae8ee6929ea55398ea3e01eb0e0f3e534f5b3557ff8f77a5e1e520dccf", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1ea38ac3807aecd79e5346b3cc43e36800613323821f4b06225c82e68e9e0657", "generation_seconds_batch": 15.821734795928933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5010786056518555, "target_z": 3.5625000730757974, "ce": 5.522225379943848, "genuineness": 3.9676074981689453, "identity": 0.6386227607727051, "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_Fear/251c97ae8ee6929ea55398ea3e01eb0e0f3e534f5b3557ff8f77a5e1e520dccf.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "2572f4c97845dcd2869c5803cf66a9dc7a052883d29e878e622a87b2bc304327", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0025a8ec4411de9a4f0e5fe44c340f41c81e800a23ed74d1325d7fd596d6e1c7", "generation_seconds_batch": 20.03522222302854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9430499076843262, "target_z": 1.0156249695517512, "ce": 5.454712867736816, "genuineness": 4.20609712600708, "identity": 0.647631824016571, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2572f4c97845dcd2869c5803cf66a9dc7a052883d29e878e622a87b2bc304327.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "25d7b3c8a2e10df8b84fa6b32f32855fcda825957aefae97285fa46a998a86a6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6d1263f4e71f1a64f2d26a73348b2f3bb14c6cc73f979c795843448c4c691d26", "generation_seconds_batch": 21.900769125903025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046944499015808105, "target_z": -0.4492187515224124, "ce": 5.847874641418457, "genuineness": 4.406930446624756, "identity": 0.6342867016792297, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/25d7b3c8a2e10df8b84fa6b32f32855fcda825957aefae97285fa46a998a86a6.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "2687f41970cec21bdde30db2b414ee64d8f17744e60eef9bb1ab86bcd3e89055", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "aece9042795c16d6336f39a747f3ae9982786670b644b96590296b2ea3ea03bc", "generation_seconds_batch": 22.411851519951597, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1861395388841629, "target_z": -0.2216796939702529, "ce": 6.23706579208374, "genuineness": 3.7165660858154297, "identity": 0.504362940788269, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2687f41970cec21bdde30db2b414ee64d8f17744e60eef9bb1ab86bcd3e89055.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "71237e9a3d9d06a1b0a5ce6553d39088e800c46d93365d3eda166582edd36be5", "generation_seconds_batch": 17.07335184898693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.010406255722045898, "target_z": -0.542968763701712, "ce": 6.41180419921875, "genuineness": 4.3504462242126465, "identity": 0.2770686447620392, "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_Fear/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.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": "26f0cbb0a3a42162294cc97aca98f005ea15eea8a068754c044f1f624e4692ec", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d347c9234cb42125a38f891eca8359901eef181dd7c4267f419640d60782114c", "generation_seconds_batch": 16.481527063064277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032606810331344604, "target_z": -0.4726562545672373, "ce": 5.998785495758057, "genuineness": 4.293961524963379, "identity": 0.6008021831512451, "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_Fear/26f0cbb0a3a42162294cc97aca98f005ea15eea8a068754c044f1f624e4692ec.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "271da35a4e2610e0180ef23ea46ee69ed08def7da1d22d1bb3d50af9500e59ac", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ebcdcc1565a9436042b61a503e91b97599a139a528266c5244f37ce43bcc9a23", "generation_seconds_batch": 22.17413131892681, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.663572311401367, "target_z": 3.828124945193152, "ce": 5.831989288330078, "genuineness": 4.149612903594971, "identity": 0.6117783784866333, "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_Fear/271da35a4e2610e0180ef23ea46ee69ed08def7da1d22d1bb3d50af9500e59ac.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": "27879becedf461d5bd686abb1378051c3f5f2b7472731d0f036b0a5940bb7fdd", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "782592d03cc15351f59b9efe42271e5e1ee760d785be60d459545f93a01be017", "generation_seconds_batch": 15.930342082981952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06367179751396179, "target_z": -0.4218750060896498, "ce": 6.062326908111572, "genuineness": 4.457139015197754, "identity": 0.527808666229248, "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_Fear/27879becedf461d5bd686abb1378051c3f5f2b7472731d0f036b0a5940bb7fdd.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": "279dbccf1895b696d2286a0d2e21293a22ea8c357c68269e93809d265e4bbff5", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ef549412394115ec912444bf26ef7ad0ccc8b5c503700d8f73f28e2e6db2154d", "generation_seconds_batch": 15.167716562049463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1706070452928543, "target_z": -0.24707031820904668, "ce": 6.0305562019348145, "genuineness": 4.268857479095459, "identity": 0.3788719177246094, "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_Fear/279dbccf1895b696d2286a0d2e21293a22ea8c357c68269e93809d265e4bbff5.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "2814334338559135cd32d07331ff0a5eeb0bdf89fa90c7db63dac79bd401412e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "676ad7394d2eae48a7e6c6f0027fe201b5e99be6387c7f96b82cf3faab45dee8", "generation_seconds_batch": 16.825836039031856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29650986194610596, "target_z": -0.04125976438803989, "ce": 6.1894097328186035, "genuineness": 4.293961524963379, "identity": 0.7909165620803833, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2814334338559135cd32d07331ff0a5eeb0bdf89fa90c7db63dac79bd401412e.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "28d364f1e15bcd9d27675246cdfd4c5c21c77c6d85582ee54e032b0336927849", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6bf547afc0d7b616aa3b7760c2a2450f3297ff00677d2852cccbf78ca0f6a0ba", "generation_seconds_batch": 22.15067121805623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6157801151275635, "target_z": 3.7500000974343966, "ce": 5.210475444793701, "genuineness": 3.7040140628814697, "identity": 0.7076196670532227, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Tu reviens. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.5, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/28d364f1e15bcd9d27675246cdfd4c5c21c77c6d85582ee54e032b0336927849.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "28f3c748d0504ed556b4e39ab16d29ba1192b191cd71450aee8cb7ffe4a648e4", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3ecfe2a61c34ccb4e37b0a02ac898adae23874414a5a706ace613fd6451e83e9", "generation_seconds_batch": 22.603372605051845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04455488920211792, "target_z": -0.4531249939103502, "ce": 6.316492557525635, "genuineness": 4.394378662109375, "identity": 0.6201953291893005, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/28f3c748d0504ed556b4e39ab16d29ba1192b191cd71450aee8cb7ffe4a648e4.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "290aaf79e9e5a4e1ce7370e63f63f73386714e4b9f7da6bffb60225ba175f0d8", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "65468d98e1ee5dfd4af8527c1729e2d95f66355de3912bc7f49539c0994c5455", "generation_seconds_batch": 25.09575701295398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4035944640636444, "target_z": 0.1337890697314591, "ce": 5.903473377227783, "genuineness": 4.231201171875, "identity": 0.7109372019767761, "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_Fear/290aaf79e9e5a4e1ce7370e63f63f73386714e4b9f7da6bffb60225ba175f0d8.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": "292bb8e9676a635ecb2b64621a29bd93f73f991434205feb1089f4c932d7a8c2", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "301c4af263bf6aa23e4ebcdbc477d3d583b2281bbcb8c59889580d3cec8dcae1", "generation_seconds_batch": 15.705862830975093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12221735715866089, "target_z": -0.3261718727163813, "ce": 6.213237762451172, "genuineness": 3.452972412109375, "identity": 0.6187596321105957, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/292bb8e9676a635ecb2b64621a29bd93f73f991434205feb1089f4c932d7a8c2.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "29d5d514ba8348b70039795af2a5c2920dedce0425fab545e4f239bd20de9f9b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "eb805785017d8160d623070bf703f869c9420acf199ab9988938bcb3a7a064a8", "generation_seconds_batch": 16.29864923004061, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8893373012542725, "target_z": 2.5625000730757974, "ce": 6.157639026641846, "genuineness": 3.7793264389038086, "identity": 0.31803882122039795, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/29d5d514ba8348b70039795af2a5c2920dedce0425fab545e4f239bd20de9f9b.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "2a08598f5e362ddceea7388460da987805fbbcc53720660657bf5d2f8bf6aa40", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8ce48b382de5a79dbf76841293ab65cfc5d1e5377a510c13f10fb6318e55fb48", "generation_seconds_batch": 22.242242051986977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9753633737564087, "target_z": 2.7031249939103503, "ce": 6.078212261199951, "genuineness": 4.256305694580078, "identity": 0.6493896842002869, "hypothesis": "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_Fear/2a08598f5e362ddceea7388460da987805fbbcc53720660657bf5d2f8bf6aa40.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": "2a7ce991cc873ef6fd56337304413a7b6c4f635c9bb428c89c00fe69c3794e68", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0052019044e1d456b741e2756839dc3daa43b2a521164d2bad87df9678214f1a", "generation_seconds_batch": 21.630088313948363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7650773525238037, "target_z": 2.359375079165447, "ce": 5.804190158843994, "genuineness": 3.8671910762786865, "identity": 0.6994233727455139, "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_Fear/2a7ce991cc873ef6fd56337304413a7b6c4f635c9bb428c89c00fe69c3794e68.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": "2b03a2e946be1552c2bab688a63319d23e81b38d57c9214e05fb2fa2abcf56f2", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e1d04419e42385b432f9d7fdccb4fedd7060dc95782149d4e08c014bda1131c1", "generation_seconds_batch": 14.686002915957943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5930250883102417, "target_z": 2.0781250426275486, "ce": 6.284721851348877, "genuineness": 3.948779582977295, "identity": 0.36049556732177734, "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_Fear/2b03a2e946be1552c2bab688a63319d23e81b38d57c9214e05fb2fa2abcf56f2.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": "2b0b314d7455da8b1bedc0cf124d6f783df89ad35905fc10bc1e5b8898d8549c", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "30c2c658c25f5e7f4cf1b412d2a22bdfbb94d7fe517d9a2755ec92f0fea69de5", "generation_seconds_batch": 16.360340956947766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7650773525238037, "target_z": 2.359375079165447, "ce": 5.839932441711426, "genuineness": 4.030367851257324, "identity": 0.5300440788269043, "hypothesis": "Die Schlüsse liegen auf dem Küchentisch. Ich suchte. In der Schublade. Dann neben dem Fenster. Nimm sie mit, wenn du gehst. Nimm sie mit, wenn du gehst.", "wer": 0.3333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2b0b314d7455da8b1bedc0cf124d6f783df89ad35905fc10bc1e5b8898d8549c.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "2b772dc29dccf86d085b19ca7bb208f77fd2fe8c4e8f9fc069868b437c9ee5bc", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "068838655a1a1ba1470b311c0af76118e0f9c97315be52ed779f606bc9cc9516", "generation_seconds_batch": 22.02204328496009, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06964585185050964, "target_z": -0.4121093514026071, "ce": 6.109982967376709, "genuineness": 4.607763767242432, "identity": 0.4734717011451721, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2b772dc29dccf86d085b19ca7bb208f77fd2fe8c4e8f9fc069868b437c9ee5bc.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "2bbd6a79024536e841669896fa4ea57df03d878c7db73b5cbe42af88775008c6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "773fd076a81d243aa95a21ab5297c5bdd949264b184be668ad0c5c40b7a19975", "generation_seconds_batch": 22.377886679023504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7650773525238037, "target_z": 2.359375079165447, "ce": 5.919358730316162, "genuineness": 3.7165660858154297, "identity": 0.2494223266839981, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2bbd6a79024536e841669896fa4ea57df03d878c7db73b5cbe42af88775008c6.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "2c2f4a967b9596d18324724d336ea6c317ef10ead5876e9dad7fef2a449dc76c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "77470a63b2f2e7d16a5c973555cff47b2714fb19ee2ebe99bdbd6372e3e2de66", "generation_seconds_batch": 21.733973794966005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2357240468263626, "target_z": -0.14062499391035022, "ce": 5.824047088623047, "genuineness": 4.457139015197754, "identity": 0.4965597987174988, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2c2f4a967b9596d18324724d336ea6c317ef10ead5876e9dad7fef2a449dc76c.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "2cbb9eec6a409dc08b71b19e686c6c32c551ec5cb1f9035f8a333875be76ff30", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "dae771a76e08aac398aea0e32be1b5cbdafaa691cf9e283357dd0c256f4f9260", "generation_seconds_batch": 15.776296164025553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1569740772247314, "target_z": 3.0, "ce": 5.007937431335449, "genuineness": 3.6412534713745117, "identity": 0.4909950792789459, "hypothesis": "La porte t'es encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. C'est bon, je suis petite prutman tool. Tire, tire, tu me prutes.", "wer": 0.7222222222222222, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2cbb9eec6a409dc08b71b19e686c6c32c551ec5cb1f9035f8a333875be76ff30.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "2cef6ed35278ebc73faad7a0febc639c10a406c3bf3d3f3777638875419a7064", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "fae250415eb98083f93f54fe011572b074c8da740065b2d1a0f9d5592b05515b", "generation_seconds_batch": 16.164207125082612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08159391582012177, "target_z": -0.3925781151043191, "ce": 6.109982967376709, "genuineness": 4.457139015197754, "identity": 0.3544256389141083, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2cef6ed35278ebc73faad7a0febc639c10a406c3bf3d3f3777638875419a7064.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "2dbea3b3cbbbab600314204122159082076a6e05aaff2bdbbad4c4dd7246ef51", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "31119250201941d7e5f719d01ef506e6f918a413c9405e49434e08037aaec97c", "generation_seconds_batch": 20.09012075001374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.965804934501648, "target_z": 2.687500024358599, "ce": 5.5659098625183105, "genuineness": 4.193545341491699, "identity": 0.7358714938163757, "hypothesis": "La porte 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_Fear/2dbea3b3cbbbab600314204122159082076a6e05aaff2bdbbad4c4dd7246ef51.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "2dd25c859c3fce8c548d7ecd70aba854d6aa030ba65d30ef851f02eab6c79c9f", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3d351f3bafa5f8eb2a900325a57d0c66b859d3218363fc50e0a75cc7a56f8908", "generation_seconds_batch": 22.218551547033712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8809199333190918, "target_z": 0.914062472596576, "ce": 5.538110733032227, "genuineness": 4.256305694580078, "identity": 0.43825966119766235, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2dd25c859c3fce8c548d7ecd70aba854d6aa030ba65d30ef851f02eab6c79c9f.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "2decb511a6449b9e33842d9939239117134658a75f60b1bf6ea4629dba33f447", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3f8087615b8fc94e6d9d886e3c7fb883bdc20bf8e9df6d8aab74e2adfa7990ae", "generation_seconds_batch": 21.018805671017617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9215434193611145, "target_z": 0.9804687880603111, "ce": 5.696964263916016, "genuineness": 4.457139015197754, "identity": 0.7974333763122559, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2decb511a6449b9e33842d9939239117134658a75f60b1bf6ea4629dba33f447.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "2e2f901c16944510126567b0c023916a60ec245fa8fa3168f271713bc170b65b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2e3b58eb86e2b81e7b217f83d3fd1badefb30e62ecb4231026b4dc1ae0f5e911", "generation_seconds_batch": 21.80854282702785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.739932656288147, "target_z": 0.6835936845362649, "ce": 6.268836498260498, "genuineness": 4.093128204345703, "identity": 0.585270881652832, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2e2f901c16944510126567b0c023916a60ec245fa8fa3168f271713bc170b65b.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "2ed232065810606d355b6717cbf680361b71faa4c484a1b6ec807c6c79cf2db5", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c5a8a590913699055690ae6baa16f63de645d795491e9e8f6bde341dd016ee48", "generation_seconds_batch": 23.469891625922173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22736039757728577, "target_z": -0.15429686662673156, "ce": 6.0146708488464355, "genuineness": 3.998987913131714, "identity": 0.4477390646934509, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2ed232065810606d355b6717cbf680361b71faa4c484a1b6ec807c6c79cf2db5.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "2ee129a5b2aca7b1774a2f7c1da1585edcd58d79cc505af1e014c3d83fc33fd0", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4a7549fc07f1da5a852c18e5bf4c133aca45323dc4a857a505026410cf7e2819", "generation_seconds_batch": 14.941641364945099, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9981184005737305, "target_z": 4.375000048717198, "ce": 5.80021858215332, "genuineness": 3.5188708305358887, "identity": 0.46298226714134216, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2ee129a5b2aca7b1774a2f7c1da1585edcd58d79cc505af1e014c3d83fc33fd0.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "2f4e3549e39ab80c20b1bf78d72792742a819c26eb265acefdbc83d43a4e28c9", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "94d7205fc966b3655200c5087dc4d41741435338e1c7887b846121a8a7a6986d", "generation_seconds_batch": 16.85675903200172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08876276016235352, "target_z": -0.38085936358190664, "ce": 5.935244083404541, "genuineness": 4.595211505889893, "identity": 0.7153593301773071, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2f4e3549e39ab80c20b1bf78d72792742a819c26eb265acefdbc83d43a4e28c9.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "2f5c13e334d94f18b67b0d9f475a75b1839f3ebd20171946d193d39e720cd2ce", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "fecfa48afc04f34ce119154b152d31b092ad523412016db0850d3978533dc1ad", "generation_seconds_batch": 15.6141521850368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1365550458431244, "target_z": -0.3027343696715564, "ce": 6.173524379730225, "genuineness": 4.432034492492676, "identity": 0.6183106899261475, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/2f5c13e334d94f18b67b0d9f475a75b1839f3ebd20171946d193d39e720cd2ce.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "310ec426383228fecba6953c3f14a24ddf7034e814f4bd30f0cca71a83ee51d9", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1cc75327b0b5e07319cd94e0ddb10962ac83250d0e47827e6410eb911ae376f2", "generation_seconds_batch": 21.82246673607733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.027133554220199585, "target_z": -0.5703125091344746, "ce": 6.348263263702393, "genuineness": 4.570107460021973, "identity": 0.6594326496124268, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/310ec426383228fecba6953c3f14a24ddf7034e814f4bd30f0cca71a83ee51d9.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "3142badfb633b9d54e709a2897eefda00200794711898b2093130316767f25e4", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "945f76119c6f7860b629cc716405dca96cfc6467978de71598ec613292d3376e", "generation_seconds_batch": 22.1630537789315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08995756506919861, "target_z": -0.3789062423879378, "ce": 6.141753673553467, "genuineness": 4.017816066741943, "identity": 0.7321898341178894, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/3142badfb633b9d54e709a2897eefda00200794711898b2093130316767f25e4.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": "31869fc1dcb18b53ec8292ffc1a6f381a6759a1393a52d94f2b845820de91d80", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ece94b6954294deae82706a9104af446c8bc8be299415084a3c1f164d085763", "generation_seconds_batch": 16.360340956947766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.367260217666626, "target_z": 3.343750109613696, "ce": 5.974957466125488, "genuineness": 3.7416701316833496, "identity": 0.5714257955551147, "hypothesis": "Die Schlüsse liegen auf dem Küchentisch. Ich suchte in der Schublade, dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "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_Fear/31869fc1dcb18b53ec8292ffc1a6f381a6759a1393a52d94f2b845820de91d80.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": "31d35fe7010dd61a83e251c0f36606d1b528825f807fbb2d2f7b4b8d0f522c5c", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e3b218b66078646a8a67520a456299dbdfa1971305011b94f1ffed1506024c69", "generation_seconds_batch": 26.38773941702675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1485567092895508, "target_z": 1.3515623995207786, "ce": 5.855817794799805, "genuineness": 3.8420867919921875, "identity": 0.7962262034416199, "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_Fear/31d35fe7010dd61a83e251c0f36606d1b528825f807fbb2d2f7b4b8d0f522c5c.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "320326a5bc2517f8f53916b2815130c093488d8bb74a74fa0deb163e14b3d785", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "07aeb957ec5e57db80222dbb89cf57d1a295b8fa2f0ce856f1b907fd057a0b02", "generation_seconds_batch": 20.657649794011377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4628448486328125, "target_z": 3.500000194868793, "ce": 5.414999485015869, "genuineness": 4.137060642242432, "identity": 0.5181137323379517, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/320326a5bc2517f8f53916b2815130c093488d8bb74a74fa0deb163e14b3d785.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "328dc0e4d6e900beb6f5d8d382ba8009184f8f75f451daa60540f0ba3789cfa0", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d32826dbf13f40ae5807a5eccc6d64ca07b74917f5c499c77f3e8ff6b7fc5799", "generation_seconds_batch": 22.98661202006042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1724529266357422, "target_z": 1.3906250182689492, "ce": 6.086154937744141, "genuineness": 4.055472373962402, "identity": 0.6937441825866699, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/328dc0e4d6e900beb6f5d8d382ba8009184f8f75f451daa60540f0ba3789cfa0.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "329c4ccc9ce1aaa6ec7fe790caabca134c60368edf30dee6b9e4ce472906fe38", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4951f3942688c8ba4c3b7868fdc2df00bc812a5834c09cf407eaa33777e0baf9", "generation_seconds_batch": 21.639668219024315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0577514171600342, "target_z": 1.2031249939103503, "ce": 5.77639102935791, "genuineness": 4.645420074462891, "identity": 0.7477049827575684, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/329c4ccc9ce1aaa6ec7fe790caabca134c60368edf30dee6b9e4ce472906fe38.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": "32a1550aee560b6ea841ce3cf7dd24b71db89f1a60a7731fd26b6a199e522061", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "753e48f187b7e925bec69c7ea3e7d7a8801a272de5d5408b9aa219ddf1029629", "generation_seconds_batch": 16.672528057009913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0529721975326538, "target_z": 1.1953125091344747, "ce": 5.661221981048584, "genuineness": 4.218649387359619, "identity": 0.561570405960083, "hypothesis": "Die Straße führt hinter der Brücke nach links. Kiew heute bis zu dem 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_Fear/32a1550aee560b6ea841ce3cf7dd24b71db89f1a60a7731fd26b6a199e522061.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": "33440b291fb5b29e1d92b6c0b95c6cb0459de009c122fcf26cdc897a15f8a34d", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c1073fa2521596e098469f965d0735698de5014ac060771c44c441d67eac3a08", "generation_seconds_batch": 22.353764098952524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6540138721466064, "target_z": 3.812499975641401, "ce": 5.661221981048584, "genuineness": 3.6349775791168213, "identity": 0.054600752890110016, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon. Zeg maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/33440b291fb5b29e1d92b6c0b95c6cb0459de009c122fcf26cdc897a15f8a34d.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "433a3c209fc9af87db62a2621a5fb39b25fc5fa5bdce2ee222a05f3fdf688575", "generation_seconds_batch": 13.501946186996065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06486660242080688, "target_z": -0.4199218848956809, "ce": 6.125868320465088, "genuineness": 4.18099308013916, "identity": 0.6776073575019836, "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_Fear/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "340b120c924a060f06019693b3e71e6d4a553504e2296e8086f75dcc9ab6d935", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9d7d65c8e43080a1dfacf42c974b10d64569b02d9a0bcd58c331a7485fdd7d4d", "generation_seconds_batch": 21.900769125903025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04336008429527283, "target_z": -0.4550781151043191, "ce": 6.0305562019348145, "genuineness": 4.256305694580078, "identity": 0.53070068359375, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/340b120c924a060f06019693b3e71e6d4a553504e2296e8086f75dcc9ab6d935.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "34388dbcf9ab1293fbb0bf3248cf5b41915c321baeaabc02a14d9ddd438bc871", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9e7aebec512274649c114f6d76a54aafb2c4ef7e2a240f799e25c9307683a970", "generation_seconds_batch": 22.041995184961706, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6778026819229126, "target_z": 0.5820311875810897, "ce": 6.046441555023193, "genuineness": 4.193545341491699, "identity": 0.4340778887271881, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/34388dbcf9ab1293fbb0bf3248cf5b41915c321baeaabc02a14d9ddd438bc871.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "8252d0af769fc500c407108dfe1abd242d056f19c7d06adeae6fca17b6da6233", "generation_seconds_batch": 15.893842538935132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0039314329624176025, "target_z": -0.5195312606568872, "ce": 6.38003396987915, "genuineness": 3.9550557136535645, "identity": 0.33835291862487793, "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_Fear/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.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": "34d4c95f3f60ec51f80fb8ef58568a8a3a70b4e0da647806892b31a594e699d8", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "763aee242cfc9b3e166eded3f0af9f0cdb602fdf3ae31bd6eace4c8b95a365d1", "generation_seconds_batch": 18.40502792899497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6157801151275635, "target_z": 3.7500000974343966, "ce": 5.526196479797363, "genuineness": 3.5471129417419434, "identity": 0.4201955795288086, "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_Fear/34d4c95f3f60ec51f80fb8ef58568a8a3a70b4e0da647806892b31a594e699d8.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "34e21ab829a3409942091df332ef1e800772f8b59226a7a68e52b152a238da6b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "582804ee1aa93c4e185972139ee82fdbcd393dc6ec22b6b87b7b8ebc2490054e", "generation_seconds_batch": 22.555160978925414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6706339120864868, "target_z": 0.5703125578516729, "ce": 5.772419452667236, "genuineness": 4.457139015197754, "identity": 0.36472636461257935, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/34e21ab829a3409942091df332ef1e800772f8b59226a7a68e52b152a238da6b.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "351b3c09e82059943f7c1005bcc15896c15d03f62af6b3067e29f89c95a99866", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5cb554e516176c5efe23f591b2e7bacf9bbe3f7de958336b641b6994d9960aab", "generation_seconds_batch": 21.639668219024315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4246108531951904, "target_z": 3.4374999269242026, "ce": 6.0305562019348145, "genuineness": 3.9676074981689453, "identity": 0.5613303184509277, "hypothesis": "La porte 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_Fear/351b3c09e82059943f7c1005bcc15896c15d03f62af6b3067e29f89c95a99866.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "3599de416d63f0cef291b819af64d8e01a726b057061219a5a52129a9573bfd8", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1edf4c03d8820bca10bd74ef09392db9ebdff6d689b142fb3aa299d14ee7041c", "generation_seconds_batch": 21.566778216976672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09951601922512054, "target_z": -0.3632812484775876, "ce": 5.903473377227783, "genuineness": 4.457139015197754, "identity": 0.36936599016189575, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/3599de416d63f0cef291b819af64d8e01a726b057061219a5a52129a9573bfd8.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "359ec0884fd69c0acd1b4c02964072d5fcec9fc15b05432ad5774a8309960a70", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bcb52b6d99a04833aec7d1f447127bed4f93e413609280ff0f825ba7f9693006", "generation_seconds_batch": 23.47531853802502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3079352080821991, "target_z": -0.022583003387988833, "ce": 5.982900142669678, "genuineness": 4.65797233581543, "identity": 0.3384460210800171, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/359ec0884fd69c0acd1b4c02964072d5fcec9fc15b05432ad5774a8309960a70.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "35b4f888c58ed58a13c22c9582ba2c69d6b9f5ca6fb42257df2afe52cf520339", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "17d11fb44acd6f3081bc6bea32516502a2514df433ddcb915929baa99a5ebe66", "generation_seconds_batch": 21.619219220010564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22437337040901184, "target_z": -0.1591796939702529, "ce": 6.070269584655762, "genuineness": 4.18099308013916, "identity": 0.7382202744483948, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oud het stond naast het oude raam. We kunnen er samen in kijken.", "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_Fear/35b4f888c58ed58a13c22c9582ba2c69d6b9f5ca6fb42257df2afe52cf520339.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": "35d11d0224367f421e0b7b1a85272f19c547db177e9fc10a90cc669bdbda7318", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6682def15f7377ae18f4f640a18c94f7d8e70c3388d06068ff663610479f595a", "generation_seconds_batch": 17.66154548607301, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8606618642807007, "target_z": 2.515624969551751, "ce": 5.816103935241699, "genuineness": 3.9801597595214844, "identity": 0.6468662023544312, "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_Fear/35d11d0224367f421e0b7b1a85272f19c547db177e9fc10a90cc669bdbda7318.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "3667080974133911fc01db2067d8ae4726d68a486bae8f3c59c898ada21f6edf", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7c9021f0874a7cdfaad30157a3a03999be429ad6512d8d1cb0fa75d48eaa8a5d", "generation_seconds_batch": 21.15058339596726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6826891899108887, "target_z": 3.8593748842966544, "ce": 5.665193557739258, "genuineness": 3.7793264389038086, "identity": 0.4996975064277649, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime, ¿cuándo estás listo?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/3667080974133911fc01db2067d8ae4726d68a486bae8f3c59c898ada21f6edf.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "36b91825caedaab7d9e98d4a5f73de46093af20677ddb26b23a9995bcc423e24", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9d82ed0919a72d4ab493f548bc488763cc4d1d936a7a17736150f3c7a637c698", "generation_seconds_batch": 21.62508882698603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.558322012424469, "target_z": 0.38671877588101156, "ce": 5.927301406860352, "genuineness": 4.570107460021973, "identity": 0.6655420064926147, "hypothesis": "J'ai trouvé la petite boîte. Elle était elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/36b91825caedaab7d9e98d4a5f73de46093af20677ddb26b23a9995bcc423e24.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "36fb2b54e3abf31d77edf527d065b1de5d55c25c5966f2b79a6f6f73943e232b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7a03e90e833cb5ab2f7153137b3c00f4effea9337d79313fe2d284d740fc81b3", "generation_seconds_batch": 15.684888810967095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2381136566400528, "target_z": -0.13671875152241245, "ce": 5.990842819213867, "genuineness": 4.18099308013916, "identity": 0.7524687647819519, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/36fb2b54e3abf31d77edf527d065b1de5d55c25c5966f2b79a6f6f73943e232b.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "36fba853fa7d63e9e01432d85c77aa3e644cc58f1d53d00ce1c42ae304b92f33", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "556345eb0095887350a10e5fe58471edf82db449cd9daed01b6ffeeafec02bb0", "generation_seconds_batch": 21.615502179018222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5834129452705383, "target_z": 0.4277343696715564, "ce": 5.796247482299805, "genuineness": 4.557555198669434, "identity": 0.5598465204238892, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Vier, 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_Fear/36fba853fa7d63e9e01432d85c77aa3e644cc58f1d53d00ce1c42ae304b92f33.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "377742091ce6d716565e7d80541d63d6036cc998ba089db37e6fc1a84f150cfc", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ce1cfd36ad7c5bcf705aa1beb3d0de6be41e7b46b893fbfb1883a29ff7766e12", "generation_seconds_batch": 21.30179176304955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006321042776107788, "target_z": -0.5156250182689494, "ce": 6.054384231567383, "genuineness": 3.6914620399475098, "identity": 0.15862610936164856, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/377742091ce6d716565e7d80541d63d6036cc998ba089db37e6fc1a84f150cfc.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "37b74d6d86c194f76b73071c0883bda19896fe103fe532e644ae0a04e09c8a82", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0ea4546ae4b7119a1391813ab624becc6a56edc3a74ffd84a60569338c615df0", "generation_seconds_batch": 22.427691484917887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003237396478652954, "target_z": -0.5312499878207004, "ce": 6.3641486167907715, "genuineness": 4.582659721374512, "identity": 0.6569893956184387, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/37b74d6d86c194f76b73071c0883bda19896fe103fe532e644ae0a04e09c8a82.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": "37c792de60583f4afefbfecc5a931c3e4dc2e3edc82d5dd0db0c473c643a2ea5", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd6995998a52caa1dff1be56deecd0291f493e13b72fe3253c3a68a80065b026", "generation_seconds_batch": 22.155466479016468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.526115894317627, "target_z": 1.9687500608964978, "ce": 5.831989288330078, "genuineness": 3.4466962814331055, "identity": 0.09966108202934265, "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_Fear/37c792de60583f4afefbfecc5a931c3e4dc2e3edc82d5dd0db0c473c643a2ea5.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "3838ba23eac6b6398c18757e640505aa27029619f3e2e15ff92b8824c3ef08e7", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "999d43cae0fb63001a736f25621826978f4af50988b85ec291089f409837f4f1", "generation_seconds_batch": 15.58970342995599, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0338016152381897, "target_z": -0.47070313337326847, "ce": 6.332377910614014, "genuineness": 4.570107460021973, "identity": 0.5279513597488403, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/3838ba23eac6b6398c18757e640505aa27029619f3e2e15ff92b8824c3ef08e7.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "383e8f8643d999b651f70c58beb058399f50082a06ce0d1d77159ff3f31fe9d9", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ecdbe37f63a1259d26941537bf0eab861d0797c604cd7437efe19e1098b04f5c", "generation_seconds_batch": 18.092481415951625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023048341274261475, "target_z": -0.48828127283618666, "ce": 6.157639026641846, "genuineness": 4.7332844734191895, "identity": 0.5211323499679565, "hypothesis": "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_Fear/383e8f8643d999b651f70c58beb058399f50082a06ce0d1d77159ff3f31fe9d9.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "38658ff04e271ec0257dc238f60ba87e78b57ea9b7995e6bd110200eeaabc968", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "782c411fd9d8c64fd063a8447cafee68f50156d429356a8cfb87403c3a35787f", "generation_seconds_batch": 20.949759008944966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11863292753696442, "target_z": -0.3320312606568871, "ce": 6.173524379730225, "genuineness": 4.2249250411987305, "identity": 0.7032252550125122, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/38658ff04e271ec0257dc238f60ba87e78b57ea9b7995e6bd110200eeaabc968.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "388b637b4aaa7d301b2c850a841ec290c00c04dcdc655d16aae4b5977cd43c84", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2325e8de77cacc39eb92d6cdb38b7ecca9c2daa312e3b2beb8cf147b2bbe2425", "generation_seconds_batch": 22.447419931995682, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8834168910980225, "target_z": 4.187500024358599, "ce": 5.871703147888184, "genuineness": 3.6287014484405518, "identity": 0.5492901802062988, "hypothesis": "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_Fear/388b637b4aaa7d301b2c850a841ec290c00c04dcdc655d16aae4b5977cd43c84.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "3892a08e0156db4fa1164f83b5341b7ccecb2018c7f12b62e1121b84f91a5d39", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e818bc22ee156422ec0485cdfc4447def0dceda3000d981ee33ecbbaff49a08b", "generation_seconds_batch": 15.796172596979886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6180623769760132, "target_z": 0.48437503044824887, "ce": 5.855817794799805, "genuineness": 4.394378662109375, "identity": 0.5603327751159668, "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_Fear/3892a08e0156db4fa1164f83b5341b7ccecb2018c7f12b62e1121b84f91a5d39.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "38c5dc5e6494e538a465ffe8adec6834dc92e4cf82db1db64b82c4e472ebfc51", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2a44d7a39308206b0e385dae8f469d5e9b3274dd6b2ed7c17a888eee883a41f0", "generation_seconds_batch": 25.09575701295398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1939057856798172, "target_z": -0.208984381850856, "ce": 6.133810997009277, "genuineness": 4.607763767242432, "identity": 0.6431796550750732, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/38c5dc5e6494e538a465ffe8adec6834dc92e4cf82db1db64b82c4e472ebfc51.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "3980c66be4f58da92277c1ca92ab18424afb2fd7956d7f0fec91bf85143a9eb6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "4ccfa9bf95bc1a8134f3464a15e7877c5563a3746166e4195f7980789f908972", "generation_seconds_batch": 22.414709073957056, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.506998896598816, "target_z": 1.9374999269242026, "ce": 5.847874641418457, "genuineness": 4.2374773025512695, "identity": 0.6338541507720947, "hypothesis": "J'ai trouvé la 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_Fear/3980c66be4f58da92277c1ca92ab18424afb2fd7956d7f0fec91bf85143a9eb6.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "39a30a34d60cc53e1c01afbfd359f75d161ca06ab7bc255b5bdeb58e757794f3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "011e36652ff82f575d45ebf4c0782e0cea1ed1082d51b8c41aab2025cace0e7e", "generation_seconds_batch": 22.397855408024043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0864267349243164, "target_z": 1.2499999025656034, "ce": 6.022613525390625, "genuineness": 4.15588903427124, "identity": 0.47089260816574097, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/39a30a34d60cc53e1c01afbfd359f75d161ca06ab7bc255b5bdeb58e757794f3.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "39dce9259dd11c9feb38d36a83cc6aea138a8e47defc83a2106e78b8775caa14", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2655a8242f57c2292a751c965a6df3acbedd3c2fc17b0bbc2cbd372e9717146f", "generation_seconds_batch": 19.809283465030603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3445051908493042, "target_z": 1.671875054806848, "ce": 6.157639026641846, "genuineness": 4.2751336097717285, "identity": 0.6577492952346802, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/39dce9259dd11c9feb38d36a83cc6aea138a8e47defc83a2106e78b8775caa14.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "3a61146861942d0bc7c5d1ce8f3b9769ebda2ff4d7c329b1035e04c4605211cf", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e205971d48a3370d1e779f396174adb241499adef7c5f4c30eb4eaaaba65d9c9", "generation_seconds_batch": 22.041928512975574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02663278579711914, "target_z": -0.4824218605370818, "ce": 6.086154937744141, "genuineness": 4.432034492492676, "identity": 0.5424280762672424, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/3a61146861942d0bc7c5d1ce8f3b9769ebda2ff4d7c329b1035e04c4605211cf.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "3a9e7b4251f6982d7623e430c72b3530e1d615bf3ff7692b97285295897a0d2c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9edc65ac87096f4e354232daee94bdf34cb0c208129fc780cf665509074496d5", "generation_seconds_batch": 22.282004495966248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8856991529464722, "target_z": 0.9218749573724515, "ce": 6.149696350097656, "genuineness": 4.545003414154053, "identity": 0.6592759490013123, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/3a9e7b4251f6982d7623e430c72b3530e1d615bf3ff7692b97285295897a0d2c.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "3b685e160a31a5de7ea3c50bb4ad3dd99e4324a2f32d47107d65d8f4d5f58113", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "17dc5eb8376ebc4a58bc14c32ec9df9f14704825709a4b2e156746d9a45edcf1", "generation_seconds_batch": 20.938076326972805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.13785719871521, "target_z": 2.9687500608964976, "ce": 5.764476776123047, "genuineness": 3.9425034523010254, "identity": 0.49641919136047363, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. Vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/3b685e160a31a5de7ea3c50bb4ad3dd99e4324a2f32d47107d65d8f4d5f58113.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": "3b77e3b1d5851b75a6c936342f7abbaa071cfe94a3d00ec32cc6b8ae2e1b213d", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ee0e04731d07d06de78c524bdbbfde25d72b0cef2248ca0d37ba92d194965f6", "generation_seconds_batch": 22.00773494306486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5308951139450073, "target_z": 1.9765625456723734, "ce": 5.045665264129639, "genuineness": 3.490628719329834, "identity": 0.5703096389770508, "hypothesis": "Die Schlösser liegen auf dem Küchentisch. Ich suche deine Schublade. Dann nehm die mit dem Fenster. Nimm sie mit, wenn du gehst!", "wer": 0.3333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/3b77e3b1d5851b75a6c936342f7abbaa071cfe94a3d00ec32cc6b8ae2e1b213d.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "3bc23c54a987f13dd3bde410fc0108a6a12c88eedd605c9a1eed22b94ee32d85", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7a810dc7221e6eb0ec8d26103daf57ccb87b227a93422205e4c82624d5cb67ca", "generation_seconds_batch": 22.069165130960755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9944802522659302, "target_z": 2.7343749330138523, "ce": 5.2938737869262695, "genuineness": 3.5220088958740234, "identity": 0.6177273988723755, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. Vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/3bc23c54a987f13dd3bde410fc0108a6a12c88eedd605c9a1eed22b94ee32d85.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": "3c56e7dbed3b53f0294d8445dbd80b03c6091329762657bbd8d923838fe66ced", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8194e12d91f4fcf6ae6344cbc7eea74b77ec4fc6f64b33966a46c4d7497d938e", "generation_seconds_batch": 16.946217847056687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07920429110527039, "target_z": -0.396484381850856, "ce": 6.252951145172119, "genuineness": 3.898571252822876, "identity": 0.5720713138580322, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/3c56e7dbed3b53f0294d8445dbd80b03c6091329762657bbd8d923838fe66ced.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "ca472e6739cdd04893a3830c1c224dc5bf4df5db3dc552c260049df6dac096e2", "generation_seconds_batch": 14.289346968987957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013489902019500732, "target_z": -0.5039062423879378, "ce": 6.340320587158203, "genuineness": 4.281409740447998, "identity": 0.7115073800086975, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de laag en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "3c620d3939c121181f95e8d27c108e9a2e3d4306ff052ab9c6c7401c1db99622", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d6c2398971f17a9b9bcc70457659474cc77a045babc7955a7a7cc24c4a248b57", "generation_seconds_batch": 21.72035479603801, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12699659168720245, "target_z": -0.31835936358190664, "ce": 5.967014789581299, "genuineness": 4.2751336097717285, "identity": 0.6993054747581482, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/3c620d3939c121181f95e8d27c108e9a2e3d4306ff052ab9c6c7401c1db99622.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": "3d1f4c3002d9e0dad8beba31e6d02b606b1d4322e79c3f72f0de1b892e02bcdd", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d37395acadfddfa215585b97c19aebfd34d9eb973cde4681aad8c39fb855c9e8", "generation_seconds_batch": 15.710691784974188, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6503758430480957, "target_z": 2.171875054806848, "ce": 6.133810997009277, "genuineness": 3.9173994064331055, "identity": 0.1608995497226715, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het naar de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/3d1f4c3002d9e0dad8beba31e6d02b606b1d4322e79c3f72f0de1b892e02bcdd.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "3d3057fd2f1a46b9576ff58b052211d78302a1a0740b9c9e42be494dd32bcb47", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "51857586be905794ab334f25af042baa3d4c28a23c5321d11fef6e517598ecf2", "generation_seconds_batch": 20.496070613036864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8319865465164185, "target_z": 2.4687500608964976, "ce": 6.181467056274414, "genuineness": 3.5471129417419434, "identity": 0.4756471514701843, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/3d3057fd2f1a46b9576ff58b052211d78302a1a0740b9c9e42be494dd32bcb47.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "3e07505148de081bed291e5f93d51e106aa25e5128880fcb0ffdcd2b382003b3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b70a376e19a3bd8b0af5f60e7568147d1ee6b6d73fd8c9c22fd2f56b74a632c2", "generation_seconds_batch": 16.01190444303211, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.329026222229004, "target_z": 3.281249841669106, "ce": 6.109982967376709, "genuineness": 4.055472373962402, "identity": 0.6769740581512451, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/3e07505148de081bed291e5f93d51e106aa25e5128880fcb0ffdcd2b382003b3.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": "3e9574a60f16edb27e69d42935e830442cf06c066b5f8d76685b2ef537b950a0", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b7b6dfaa8bc143041a924d9ddb9551fb164143d5cb293b4b1aae1f9a5162094a", "generation_seconds_batch": 16.043422276969068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029022395610809326, "target_z": -0.478515618149144, "ce": 6.046441555023193, "genuineness": 4.168440818786621, "identity": 0.4906669855117798, "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_Fear/3e9574a60f16edb27e69d42935e830442cf06c066b5f8d76685b2ef537b950a0.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "3ec64d5e57dc25ec78e7101158296782522f7f4f846cad19c282541c65b3f06e", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "dcdd97c1b0a454e26f243246530bdcf47f53f9693891c7994fcd108373dd68ae", "generation_seconds_batch": 18.092481415951625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.056502968072891235, "target_z": -0.4335937332534631, "ce": 6.221180438995361, "genuineness": 4.6705241203308105, "identity": 0.7426749467849731, "hypothesis": "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_Fear/3ec64d5e57dc25ec78e7101158296782522f7f4f846cad19c282541c65b3f06e.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "3f25d7a37fa02ce7a138eda216ea72f1d568e1dcd4abf2c63face253a2fd4e00", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9cd03130f2fa8ccb31de25bbb26e9eb7154635aa8d4ec2ed250729746eb1fc1e", "generation_seconds_batch": 20.125497277942486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.640817403793335, "target_z": 2.1562500852550968, "ce": 5.95112943649292, "genuineness": 3.8922953605651855, "identity": 0.5210185050964355, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/3f25d7a37fa02ce7a138eda216ea72f1d568e1dcd4abf2c63face253a2fd4e00.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "3fad632e5ac731b54bf33590bf5ef66a96a046df6c6c28e8375d89886ad4dafc", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1210bab3a4e985ae3f88d33f3214f2b143762481c5ec354a97e88e162d6ce0fc", "generation_seconds_batch": 21.197157065034844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5393123626708984, "target_z": 3.6249999512828017, "ce": 5.871703147888184, "genuineness": 3.735394239425659, "identity": 0.4797232151031494, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. ¡Vieja! ¡Podemos mirar juntos lo que hay dentro!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/3fad632e5ac731b54bf33590bf5ef66a96a046df6c6c28e8375d89886ad4dafc.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "40a09dc49c158692a7b93bd9b124c485ca282901f2ba0fa458e61fe827b6eb94", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "aed1e2952bf325956ca1b3ce6f02d08be34c1bf9d6541fa38b0b8cfe07ed18c9", "generation_seconds_batch": 22.11773615598213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01707431674003601, "target_z": -0.4980468788060311, "ce": 6.395919322967529, "genuineness": 4.469690799713135, "identity": 0.7014497518539429, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/40a09dc49c158692a7b93bd9b124c485ca282901f2ba0fa458e61fe827b6eb94.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "40d51a7e63141b3ae788553644c181e4629cb3f62a3168519c352faf21b4b5a5", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "16561d1167fd745f3e9b1d3be814b78d5c0bbab3c27854b4ca7d4ddbdcf1134f", "generation_seconds_batch": 15.199476376990788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7268434762954712, "target_z": 2.2968750060896497, "ce": 6.078212261199951, "genuineness": 4.193545341491699, "identity": 0.5755826234817505, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/40d51a7e63141b3ae788553644c181e4629cb3f62a3168519c352faf21b4b5a5.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": "4155d4941efb2c651f3021ff0c7c8a81c6bc5eb79f6973bc0996ddf413e40339", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "64b341b26639afbf63ce744bb19c01925abdcca6840de9390aff9de32b5a7c9e", "generation_seconds_batch": 22.859467306057923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.540453553199768, "target_z": 1.9921875152241244, "ce": 5.760505676269531, "genuineness": 3.8922953605651855, "identity": -0.10888587683439255, "hypothesis": "De sleutels lig op de keukentafel. Ik keek in de la en daarna, naast het raam, neemt ze mee als je weggaat.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/4155d4941efb2c651f3021ff0c7c8a81c6bc5eb79f6973bc0996ddf413e40339.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": "41b1ab97f52b52e1489160ba11cd808f0eca3a51a02a0b22cca956ba4bc71c14", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2c1b2e8be61f6a02bd1bab2c021835ed0d6e01e75db9dad61f68f14ee0192328", "generation_seconds_batch": 18.701524717966095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9621668457984924, "target_z": 1.0468750060896497, "ce": 5.665193557739258, "genuineness": 4.099404335021973, "identity": 0.6102743148803711, "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_Fear/41b1ab97f52b52e1489160ba11cd808f0eca3a51a02a0b22cca956ba4bc71c14.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "41bb0335c6f2b4f359fcc1d85e0679e741eeb08d4a289a2e71f282fe01d1027c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "211c1c6a8ae4c4add8219841e79b19a160cb9a6cab629931015f0d9c33d6dab9", "generation_seconds_batch": 15.331929822918028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2643994092941284, "target_z": -0.09375001217929955, "ce": 6.022613525390625, "genuineness": 4.362998008728027, "identity": 0.47010338306427, "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_Fear/41bb0335c6f2b4f359fcc1d85e0679e741eeb08d4a289a2e71f282fe01d1027c.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "41d2e2269f160d19d397724aeeda1e51e2668397024366f6626f076ded73c9bf", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "64b968c14cf99519c4752a0f828013e79f1794e15caad6474ae518c5866ff737", "generation_seconds_batch": 21.70229421998374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21660712361335754, "target_z": -0.17187500608964978, "ce": 5.959072113037109, "genuineness": 4.325342178344727, "identity": 0.5702153444290161, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zé, een gegeven moment. Zek nu, dan is ik.", "wer": 0.47368421052631576, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/41d2e2269f160d19d397724aeeda1e51e2668397024366f6626f076ded73c9bf.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "41d78049f65e3bad30f83b7b1675c6f0f5d365130019d22633f2176a11013b38", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "95f2d8778a29129a442f2ef5d66b3239198429ae666161a087f8c898957044ea", "generation_seconds_batch": 22.255350062041543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4926612377166748, "target_z": 1.914062472596576, "ce": 5.879645347595215, "genuineness": 4.005263805389404, "identity": 0.4804411232471466, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/41d78049f65e3bad30f83b7b1675c6f0f5d365130019d22633f2176a11013b38.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "42030012b31198bc0705160bfe514a9b89dcd92af3a4ba9165071d783b2c0a03", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "784c7ef5b2356ca833514c2fd8fe83aca603b8d4bfbc66bf87292f706ea7f7c5", "generation_seconds_batch": 21.964428964070976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3422229290008545, "target_z": 4.937500121792995, "ce": 5.796247482299805, "genuineness": 3.503180742263794, "identity": 0.3400940001010895, "hypothesis": "The 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_Fear/42030012b31198bc0705160bfe514a9b89dcd92af3a4ba9165071d783b2c0a03.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "42db3c715bed8b204422d09cf192317751c52724cfebfb44652b9097c4ac63b8", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "89229d5cf877c5f157ddbb784e17a8f788b9f661f679e5d632d11c3f57613ebf", "generation_seconds_batch": 16.081018986995332, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04574969410896301, "target_z": -0.4511718727163813, "ce": 6.268836498260498, "genuineness": 4.482243061065674, "identity": 0.5683193206787109, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/42db3c715bed8b204422d09cf192317751c52724cfebfb44652b9097c4ac63b8.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "43084cf2afaa3f2346e71238557dce3725a4df455b7a74bc62545559902a55c4", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "57fffba166facaff120d4e978e6adae6ac2252e2df9f908804462cd6630a2399", "generation_seconds_batch": 15.023613129975274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06964585185050964, "target_z": -0.4121093514026071, "ce": 6.149696350097656, "genuineness": 4.758388519287109, "identity": 0.7146668434143066, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/43084cf2afaa3f2346e71238557dce3725a4df455b7a74bc62545559902a55c4.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "431c7bb552a7f0038b8da8c551822e64813c9e6c332c5cecb9cbc8702751b63b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4bf5e2a5cd06a39bfe81ab2383a06d0b34ad219e804181c4e7ce12df60291dd7", "generation_seconds_batch": 22.294266500044614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011100292205810547, "target_z": -0.5078124847758756, "ce": 6.221180438995361, "genuineness": 4.65797233581543, "identity": 0.6660871505737305, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/431c7bb552a7f0038b8da8c551822e64813c9e6c332c5cecb9cbc8702751b63b.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": "432e2ab31faaa097e054adbcec1cc44ce9f4fd4ba355e0809ca02ef4139c9784", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3a3e40ca976c7d8df3d4ad1132a3d6a03ef349349efd684d15d8a8808bfd7845", "generation_seconds_batch": 18.734013667912222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9753633737564087, "target_z": 2.7031249939103503, "ce": 5.343515396118164, "genuineness": 4.042920112609863, "identity": 0.5510538220405579, "hypothesis": "Deine Nachricht kam, als sie schon weg war. Ich lass sie zweimal. Dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.08333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/432e2ab31faaa097e054adbcec1cc44ce9f4fd4ba355e0809ca02ef4139c9784.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "5d7040971af1d4487c40cd41c28098f2c90bc5f506868cf9b3610ac7b9688ce4", "generation_seconds_batch": 13.501946186996065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03858083486557007, "target_z": -0.4628906485973929, "ce": 6.006728172302246, "genuineness": 4.532451152801514, "identity": 0.7094518542289734, "hypothesis": "De weg gaat linksaf naar de brug. Loopt verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "438e16243a543fe4e6ee2e7266446b2ee29e9e91fbc1d8cb170f99f94f75626f", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "81fae250191eded56ccceb9cb4436fbc799a2aabb33c0f2416f246385a560fe5", "generation_seconds_batch": 21.099755798000842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.739932656288147, "target_z": 0.6835936845362649, "ce": 6.1020402908325195, "genuineness": 4.030367851257324, "identity": 0.41646862030029297, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/438e16243a543fe4e6ee2e7266446b2ee29e9e91fbc1d8cb170f99f94f75626f.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "439d8156a9f3d8ffc4995238429cf160ad74faa921918acaa8df46bb5aec3945", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8e90c8e851599e251fc397217e8c292de1b315347ee7daeab5ed46cac604a25f", "generation_seconds_batch": 22.041928512975574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03977566957473755, "target_z": -0.46093747868622575, "ce": 6.197352409362793, "genuineness": 4.595211505889893, "identity": 0.6811963319778442, "hypothesis": "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_Fear/439d8156a9f3d8ffc4995238429cf160ad74faa921918acaa8df46bb5aec3945.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "d7b2341e2bccd3a7ecef674032e8bd66f1081266be898949257f37f80aaa14bc", "generation_seconds_batch": 13.829734422964975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.042165279388427734, "target_z": -0.457031236298288, "ce": 6.292664527893066, "genuineness": 4.7332844734191895, "identity": 0.6100065112113953, "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_Fear/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "440303737a1eed9643c2c9ec7083aa09020c2c5e67c98d24bf9b90f6d9cd73a0", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9d72c5f03f6509504cfdb88341b578de8b3b9f806d861b0102d668b2ddb8c360", "generation_seconds_batch": 15.736237279954366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003237396478652954, "target_z": -0.5312499878207004, "ce": 6.3641486167907715, "genuineness": 4.432034492492676, "identity": 0.542039155960083, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/440303737a1eed9643c2c9ec7083aa09020c2c5e67c98d24bf9b90f6d9cd73a0.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "4455a6841db7dbbbf71a70a29361a3f7176796f15854d043186422a490a13fdb", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "268576763353cc8b9aa685bb24cb77d041f3811de198d3a985e5abc78261f454", "generation_seconds_batch": 21.952718800050206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08278872072696686, "target_z": -0.3906249939103502, "ce": 5.998785495758057, "genuineness": 4.432034492492676, "identity": 0.6636995077133179, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/4455a6841db7dbbbf71a70a29361a3f7176796f15854d043186422a490a13fdb.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "448b9b9a84bdc80f8d97de7d2b1b2064c747b2201832bd4f210d46ad1cfcad31", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c01811ace41d5e797c54b3666ba2d654b01198ea908786abaa4ff2c39d416f5e", "generation_seconds_batch": 15.054047149955295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1353602409362793, "target_z": -0.3046874908655253, "ce": 6.165581703186035, "genuineness": 4.243753433227539, "identity": 0.6135284900665283, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/448b9b9a84bdc80f8d97de7d2b1b2064c747b2201832bd4f210d46ad1cfcad31.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "44b98c1ca77e681db4f7a0200e32fab3746310fc003bdb84af03d7b1c23ed5c6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2feaf613c5f666cbdaa44a5c5d62bb0c3b6100ffd5db5a51b4c5339cf4fabf60", "generation_seconds_batch": 21.46742834604811, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.023155689239502, "target_z": 2.7812500365378985, "ce": 5.855817794799805, "genuineness": 3.9801597595214844, "identity": 0.30111855268478394, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/44b98c1ca77e681db4f7a0200e32fab3746310fc003bdb84af03d7b1c23ed5c6.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": "4572d6fc8044fba551f856106d2777c6b3e75a2063c1df26ccaf91e1cb6c1034", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d9064c98cdb88f947d027502fdb7faf3c9eeb9504d920756bc16d8ac5f729748", "generation_seconds_batch": 16.428143683006056, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19569800794124603, "target_z": -0.20605467570130356, "ce": 6.046441555023193, "genuineness": 4.325342178344727, "identity": 0.395048052072525, "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_Fear/4572d6fc8044fba551f856106d2777c6b3e75a2063c1df26ccaf91e1cb6c1034.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": "4585d2533e1c3fdeed86294c96214296d116070f004456a27573b85b29720d14", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d415e79065dfa1c87f661dee7273763ea5832578470d757924d1d98fe11e7112", "generation_seconds_batch": 20.602992844069377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15686675906181335, "target_z": -0.2695312606568871, "ce": 5.665193557739258, "genuineness": 4.005263805389404, "identity": 0.43241527676582336, "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_Fear/4585d2533e1c3fdeed86294c96214296d116070f004456a27573b85b29720d14.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "1fcd24faa6a3f610755099d640608bbe5045c87e7799dd66a72e6d711fbca22b", "generation_seconds_batch": 16.256553636980243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08756794035434723, "target_z": -0.3828125091344747, "ce": 6.252951145172119, "genuineness": 4.432034492492676, "identity": 0.6378216743469238, "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_Fear/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "464a44aa066f19d167a51a79f89d7e1d66033de46ecbec43c61cba11e655bd38", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "39bcc9a3c7271ffb55256a51944ea967d7f50ee4eddf2e08c7790ce0118d2aa4", "generation_seconds_batch": 14.448327674064785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09473678469657898, "target_z": -0.3710937576120622, "ce": 6.260893821716309, "genuineness": 4.093128204345703, "identity": 0.43138569593429565, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/464a44aa066f19d167a51a79f89d7e1d66033de46ecbec43c61cba11e655bd38.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "46686e707df8177ba6fca11857b062f4d397ed42f440945e1539e78d0447531b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "72441a62142ce9a8405065204ae2c258771f4012303fa742a2d299abf8f43f7d", "generation_seconds_batch": 21.76435483293608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02663278579711914, "target_z": -0.4824218605370818, "ce": 6.046441555023193, "genuineness": 4.432034492492676, "identity": 0.5740465521812439, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/46686e707df8177ba6fca11857b062f4d397ed42f440945e1539e78d0447531b.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "4678fc301d0c8bb2f1070c5c513865234d3a47108fb92e5c65ef2ae9f040bcc6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e0a4f34af9b24824a637875d0304aa18ac95eac987e994bec466f4a904bab446", "generation_seconds_batch": 21.02299760002643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2059075832366943, "target_z": 1.445312606568871, "ce": 5.911416053771973, "genuineness": 4.457139015197754, "identity": 0.6314496994018555, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons garder 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_Fear/4678fc301d0c8bb2f1070c5c513865234d3a47108fb92e5c65ef2ae9f040bcc6.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "46808dcc841dde6dc2115ee5dca2edfcb971c173fa9301d169fbc9ab8165b3f2", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3e84bdf82c90d4e2cd857e94b0f4c9296a54856732e219b8e1a072fc65de9a4a", "generation_seconds_batch": 17.611082619056106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9466880559921265, "target_z": 2.6562500852550968, "ce": 5.661221981048584, "genuineness": 3.8546390533447266, "identity": 0.16819757223129272, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/46808dcc841dde6dc2115ee5dca2edfcb971c173fa9301d169fbc9ab8165b3f2.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "46dcdb7f8ca7efc6246532a97dfa1e709cbfa5c3b6a81241f1e7684f2bebf44e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d5daef6fb92d9759bff3cd1c5e005a42c2e6cde261df03c6ca62a5fcc3922878", "generation_seconds_batch": 19.14738253399264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7160365581512451, "target_z": 0.6445312606568872, "ce": 6.0305562019348145, "genuineness": 4.036643981933594, "identity": 0.6982492208480835, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/46dcdb7f8ca7efc6246532a97dfa1e709cbfa5c3b6a81241f1e7684f2bebf44e.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": "473f63257b3ee234b75bc6af03447c3f13c35cd25d830dcb16c2256e500dfd95", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "39790e453a5a3387cb77d213e6e3b75a8dc01f25303e62bc6d2e11c180bac945", "generation_seconds_batch": 21.34954846499022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0745859146118164, "target_z": 4.499999805131207, "ce": 5.756534099578857, "genuineness": 3.7165660858154297, "identity": 0.5594663023948669, "hypothesis": "La carretera gira a la izquierda, tras el puente, sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/473f63257b3ee234b75bc6af03447c3f13c35cd25d830dcb16c2256e500dfd95.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "4766482b0387e46a084a2a04efa277fc793ac1c939d20d14e6b112a8cfa0f425", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "863f7020ec9c707f73086e0c7667b72f0e4475d7fdc9a0b7cbbccb175ab158cb", "generation_seconds_batch": 21.86353756301105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1963491439819336, "target_z": 1.42968763701712, "ce": 5.391171455383301, "genuineness": 4.137060642242432, "identity": 0.6110864877700806, "hypothesis": "La porte t'as 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_Fear/4766482b0387e46a084a2a04efa277fc793ac1c939d20d14e6b112a8cfa0f425.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "47adf2aebc478fbddff7d6c92db3525f7f61648f3a9d9d87c35ec6f39cdfdf39", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8aca5278451b7b6b6baa885ae2605bcfacde91f0795bda38868c3689a964c5bf", "generation_seconds_batch": 20.385860246024095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.965804934501648, "target_z": 2.687500024358599, "ce": 5.998785495758057, "genuineness": 3.973883628845215, "identity": 0.3245464563369751, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer 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_Fear/47adf2aebc478fbddff7d6c92db3525f7f61648f3a9d9d87c35ec6f39cdfdf39.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "47bf231031d2b60592a752e46c567d7af15ff1c81275669392fadafe5be7ec20", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "582f49e18c2cd6ec9a95d5d0896575b812ca2600a76caf4d2481d095813516a2", "generation_seconds_batch": 22.48658072494436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3196592628955841, "target_z": -0.003417949910146, "ce": 6.022613525390625, "genuineness": 4.632867813110352, "identity": 0.4355296492576599, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/47bf231031d2b60592a752e46c567d7af15ff1c81275669392fadafe5be7ec20.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": "47c4355140972b71e7be96ff4af0c019138ed7fd0063bd0f2f83ffb5e819388c", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5f0ca4df9ddcec998f4b6914cedfde7615e00c5199fa427f0968f32c2c3f6b83", "generation_seconds_batch": 15.532252046046779, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8224281072616577, "target_z": 2.453125091344747, "ce": 6.197352409362793, "genuineness": 4.118232727050781, "identity": 0.5788747072219849, "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_Fear/47c4355140972b71e7be96ff4af0c019138ed7fd0063bd0f2f83ffb5e819388c.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "2557a0babccacc18043cc7ba7e3d40fbf8b3be7dea53633f38619f2a975a9ebf", "generation_seconds_batch": 16.127161253942177, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0624769926071167, "target_z": -0.4238281272836187, "ce": 6.141753673553467, "genuineness": 4.545003414154053, "identity": 0.7432689666748047, "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_Fear/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "48d09aa209e2aa3e4a542226a3a1e22049d569bc7f1b61ecaac66ebb3439bcd5", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "39fe4777360342058055a9230107a8eacf4a1ed15432a4a57d028cda7dbbc994", "generation_seconds_batch": 24.034196887048893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003237396478652954, "target_z": -0.5312499878207004, "ce": 6.284721851348877, "genuineness": 4.519899368286133, "identity": 0.27867060899734497, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/48d09aa209e2aa3e4a542226a3a1e22049d569bc7f1b61ecaac66ebb3439bcd5.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "490e06e125796d976b38d14c39757abd358974afaffc24e7d0c3c34ff19f628a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f10f3308d3d7e3efc7ba68f620f8a037ea3ab9adfd53f2272e4076c16bf1a59f", "generation_seconds_batch": 23.882364302990027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.749598503112793, "target_z": 3.9687500608964976, "ce": 5.689021587371826, "genuineness": 4.20609712600708, "identity": 0.7952841520309448, "hypothesis": "Die Tür ist noch offen. Ich hab. ich hab deinen Mantel auf den Stuhl gelegt. 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_Fear/490e06e125796d976b38d14c39757abd358974afaffc24e7d0c3c34ff19f628a.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "768fb74255ca963e40e0162fda2993846b5e89bf6f2a59602d76fde8d6e6b008", "generation_seconds_batch": 14.214368503075093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0923471748828888, "target_z": -0.375, "ce": 6.157639026641846, "genuineness": 4.281409740447998, "identity": 0.5432015657424927, "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_Fear/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "4a07612172d6e819dfe5b3568d9ec4e48a464c11d6757f4e523e142023850356", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9336f5afa7770d70eb75c342e29b0b1e4abe9e9a466caf16026a187cd1b38544", "generation_seconds_batch": 20.272556668962352, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8834168910980225, "target_z": 4.187500024358599, "ce": 5.748591423034668, "genuineness": 3.773050308227539, "identity": 0.525788426399231, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. Vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/4a07612172d6e819dfe5b3568d9ec4e48a464c11d6757f4e523e142023850356.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "4a4733d900c25fb70ca128240b3a80ec2e5618230ec10fb36ebbcf1b984c822c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4eb193c894ea4bc92e6c84d8ef5cbf62fa300e3bda55489e5ccaa6aed42edd5f", "generation_seconds_batch": 20.478479165001772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.399573564529419, "target_z": 5.031249939103502, "ce": 5.788304805755615, "genuineness": 3.998987913131714, "identity": 0.5226663947105408, "hypothesis": "J'ai trouvé la 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_Fear/4a4733d900c25fb70ca128240b3a80ec2e5618230ec10fb36ebbcf1b984c822c.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "4a62a1ee79a515b86e661c6cf0f647e0795c9a76257ad8a760c6de688207d03a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5f8f8c235391e6ad6a03c78c1a306fa203eb903b2f7b395cdc375193736b3cb2", "generation_seconds_batch": 19.836625437950715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1508927345275879, "target_z": -0.27929686662673153, "ce": 5.1052350997924805, "genuineness": 4.005263805389404, "identity": 0.3522242605686188, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/4a62a1ee79a515b86e661c6cf0f647e0795c9a76257ad8a760c6de688207d03a.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "4b610d3ee6fac3adc6972eba46778ae1d3f964445794ab9896bff8db0c7141c4", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "36b269649c461841f675dd4db793168bbca6dea37774a4ede42773e232bd3556", "generation_seconds_batch": 21.30179176304955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015879511833190918, "target_z": -0.5, "ce": 6.324435234069824, "genuineness": 4.293961524963379, "identity": 0.28966623544692993, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/4b610d3ee6fac3adc6972eba46778ae1d3f964445794ab9896bff8db0c7141c4.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "4b7256795eb6bf8b7fd0e38880b7542b734ad46386212b40c601929a94ba8194", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "133a74d348154ab466caac7fcb28ca72a817a6ec8200e9f667239bbd3446c7b2", "generation_seconds_batch": 21.790701926103793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8606618642807007, "target_z": 2.515624969551751, "ce": 6.0305562019348145, "genuineness": 4.093128204345703, "identity": 0.5537302494049072, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt, Irseno. Dis-moi quand tu es prêt.", "wer": 0.3888888888888889, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/4b7256795eb6bf8b7fd0e38880b7542b734ad46386212b40c601929a94ba8194.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "4bdcf611a5d385e5e11b373510f4974720db6f85f59be121a7052641d2d88ea9", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "535d5d809cd652690322e86e6bfc748ca9b47c9c4bf0edd1cec00452e4581823", "generation_seconds_batch": 23.647619134979323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.864300012588501, "target_z": 4.156250085255097, "ce": 5.585766792297363, "genuineness": 3.7793264389038086, "identity": 0.5558604001998901, "hypothesis": "La puerta sigue abierta. He dejado tu abrijo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/4bdcf611a5d385e5e11b373510f4974720db6f85f59be121a7052641d2d88ea9.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": "4c47bff66b2d7242fac3c41260970250a13c3c42a6ad9c77fc614222f516f63c", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4bb35db25b7623a8a3eb07a26daaebc8c8baca1982ac92cd5103d311939fd24d", "generation_seconds_batch": 15.81298807298299, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08876276016235352, "target_z": -0.38085936358190664, "ce": 6.078212261199951, "genuineness": 4.319066047668457, "identity": 0.5031651854515076, "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_Fear/4c47bff66b2d7242fac3c41260970250a13c3c42a6ad9c77fc614222f516f63c.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": "4c57800b8bfa40d8f71a4abeb55964540389eef40c955dd81d833e5c9f4a180a", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "041d7ad768b7575cf26a2abe46100c82bc4d7e95f24a43a78bb634d1d18f6bd6", "generation_seconds_batch": 16.681625318014994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5810233354568481, "target_z": 0.4238281272836187, "ce": 5.982900142669678, "genuineness": 4.099404335021973, "identity": 0.5769721865653992, "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_Fear/4c57800b8bfa40d8f71a4abeb55964540389eef40c955dd81d833e5c9f4a180a.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "4c970673763ab3ebd034c0b47c02af5a909d816e418dddc35346616467056e4f", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b781af575d13cb73735060529aa1128df8f8d4f167fbdb57af46d76b495ca80d", "generation_seconds_batch": 19.871444149990566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4890231788158417, "target_z": 0.2734375030448249, "ce": 5.847874641418457, "genuineness": 4.281409740447998, "identity": 0.30861997604370117, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/4c970673763ab3ebd034c0b47c02af5a909d816e418dddc35346616467056e4f.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "4cc366f3c071e6d898f3c2d21a91629a5c0201261f36f768ef7c422bc72b7c92", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "bdd60194e617935ad7d11fe4986c43d9d156095ae19f6e4ecaebcfe4f2074659", "generation_seconds_batch": 22.15067121805623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4246108531951904, "target_z": 3.4374999269242026, "ce": 5.871703147888184, "genuineness": 3.7667744159698486, "identity": 0.6872179508209229, "hypothesis": "The porte is encore overte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Dis-moi quand tu es prêt.", "wer": 0.5, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/4cc366f3c071e6d898f3c2d21a91629a5c0201261f36f768ef7c422bc72b7c92.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "4cff6a64e1beb0b336210efd1df6850a3c862cc5a20bb65cf5d3b7f389443e38", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e33e3930c746646544ed3f51b5d00f8cd6114a0ed9181d948ee3530eec91e5fb", "generation_seconds_batch": 20.035916161024943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3779597282409668, "target_z": 1.7265624482379769, "ce": 6.062326908111572, "genuineness": 4.406930446624756, "identity": 0.8133453726768494, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Décolis. Disher, t'es ici.", "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_Fear/4cff6a64e1beb0b336210efd1df6850a3c862cc5a20bb65cf5d3b7f389443e38.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "4d19c9fda5043afbd3b1e3d442a0b12a2803176c95088f7154c71ccd5c62005f", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8226ba8cd91421070cc0700e020a72904ef8b3b38625b6b5e13b18c27e2584b7", "generation_seconds_batch": 23.186691038077697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.001541823148727417, "target_z": -0.5234375030448248, "ce": 6.197352409362793, "genuineness": 4.168440818786621, "identity": 0.6833919286727905, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/4d19c9fda5043afbd3b1e3d442a0b12a2803176c95088f7154c71ccd5c62005f.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "4d37f38e3e7ae3da3e8d3f68b43f30df0c90e8e2358464d0603cfcb38ec27a6a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "743bae3a80b9bf534641bafc49ba9b2867f67914b22444dcb8f7168949c004d3", "generation_seconds_batch": 20.668674588901922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15328234434127808, "target_z": -0.2753906242387938, "ce": 5.736677646636963, "genuineness": 4.469690799713135, "identity": 0.6715722680091858, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/4d37f38e3e7ae3da3e8d3f68b43f30df0c90e8e2358464d0603cfcb38ec27a6a.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "4d725bce406f3e312d98c4f7771a55205885ac5d8a6b5af0f9d94b93cbffd8eb", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "38552d15961fb7c7b4ef9d085ae05c0c7bc7e40ed41861b53c2219839fbb6d24", "generation_seconds_batch": 17.694362681009807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3039889335632324, "target_z": 4.874999853848405, "ce": 5.792276382446289, "genuineness": 3.810706615447998, "identity": 0.5571626424789429, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient, ce qu'elle contient, mais mettez que c'est possible. Les Millscoeurs.", "wer": 0.5263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/4d725bce406f3e312d98c4f7771a55205885ac5d8a6b5af0f9d94b93cbffd8eb.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "4d751a8f88e029362d93b7d12483a74fd02c5f52d8cbd21347262aca3cb16115", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8fa8fb959e25f1af5eb08732d322a85b671b451d39e37c2d7ee6b62960787655", "generation_seconds_batch": 23.186691038077697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4400897026062012, "target_z": 1.828124945193152, "ce": 6.125868320465088, "genuineness": 3.998987913131714, "identity": 0.5560328364372253, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/4d751a8f88e029362d93b7d12483a74fd02c5f52d8cbd21347262aca3cb16115.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "4d8db1ab80d6e62a73cbc4e6a0804628dc5f3b31581fe5eb61ae58b655644258", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ebfb7e3e259183ae1908f4ecb4ff367a046ad58208f1b7c03f67c252b571e090", "generation_seconds_batch": 23.198714300990105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03619122505187988, "target_z": -0.46679689098533067, "ce": 6.324435234069824, "genuineness": 4.494794845581055, "identity": 0.7478452324867249, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/4d8db1ab80d6e62a73cbc4e6a0804628dc5f3b31581fe5eb61ae58b655644258.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "4f04687df00f3bfee98ae0d59f89063366e57a78b9b3f56ebdc4a7bf09e8b0b6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d7cbff2a759154b35631acd19073f99865c78678106ce98b829bd04acc1f1265", "generation_seconds_batch": 21.82246673607733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01707431674003601, "target_z": -0.4980468788060311, "ce": 6.348263263702393, "genuineness": 4.457139015197754, "identity": 0.4366411566734314, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/4f04687df00f3bfee98ae0d59f89063366e57a78b9b3f56ebdc4a7bf09e8b0b6.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "4f5b9cda5dc3cffbe37bc3fccce2deec2ab1dd3429e3bcc4c36873c397be1f66", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "392f155388bb34bb135e3ae4b0933350c0326b051eb7af50f855984c2eb12ce6", "generation_seconds_batch": 21.310944195953198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013489902019500732, "target_z": -0.5039062423879378, "ce": 6.141753673553467, "genuineness": 4.595211505889893, "identity": 0.6236954927444458, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/4f5b9cda5dc3cffbe37bc3fccce2deec2ab1dd3429e3bcc4c36873c397be1f66.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "4f6292ba0532e6d2587221596eb04583c221fc206e9afdd8de88b1f08a463d16", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1b76f2f5e4d377a049d1bb5c66829e2ec1d75637b46185d8070435704f0d96f4", "generation_seconds_batch": 23.012750147026964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.451984167098999, "target_z": 0.2128906485973929, "ce": 5.756534099578857, "genuineness": 4.218649387359619, "identity": 0.5802017450332642, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/4f6292ba0532e6d2587221596eb04583c221fc206e9afdd8de88b1f08a463d16.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": "4fdf38cb2c5d7707e66a38362f08102d6a8df0d301a311aedd453ab1fdbc97c7", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2b4c89b8493a4d63217f5bf5b8f129fe0466a90683e3dcf60db2da2a85b33ec9", "generation_seconds_batch": 20.690548429032788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.548870801925659, "target_z": 3.640624920834553, "ce": 5.7128496170043945, "genuineness": 3.8420867919921875, "identity": 0.6744749546051025, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter. Bis zu dem kleinen Holztor. Ich warte. Ich warte auf der anderen Seite, wo ich so fucking.", "wer": 0.2857142857142857, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/4fdf38cb2c5d7707e66a38362f08102d6a8df0d301a311aedd453ab1fdbc97c7.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "4ff94952bee9a09ea133509d244dc1d72e7bd6fcb93cb84f28bcd8d71ed8f76d", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "f419322b9ae1c48909bbfb4428310cc5a74d3446b2220e729dee51dcb7bab016", "generation_seconds_batch": 22.414709073957056, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.673130750656128, "target_z": 3.8437499147449032, "ce": 5.982900142669678, "genuineness": 4.049196243286133, "identity": 0.6039636731147766, "hypothesis": "J'ai trouvé la 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_Fear/4ff94952bee9a09ea133509d244dc1d72e7bd6fcb93cb84f28bcd8d71ed8f76d.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "50406b747702f1b8af8be9c9f9055f31db78c8f8b6fa446ab9dc481f59832b8c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4e07554cd5c9b23648a3d9c15e31d5a03237a5316882cbd0df7731528fcc4efb", "generation_seconds_batch": 15.141561339027248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3349467515945435, "target_z": 1.656250085255097, "ce": 5.911416053771973, "genuineness": 3.998987913131714, "identity": 0.40749818086624146, "hypothesis": "He encontrado. La cajita estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/50406b747702f1b8af8be9c9f9055f31db78c8f8b6fa446ab9dc481f59832b8c.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": "50590628a1bc7f81b3412d39ba593cf0aa2a3c1855a995ac9d3cf789541ca725", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ccd56652c324a196cf6830730e7c96064f28aadf50f35034c6c98509e1a7c07d", "generation_seconds_batch": 15.093045728979632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6347896456718445, "target_z": 0.5117187271638133, "ce": 5.796247482299805, "genuineness": 3.8169827461242676, "identity": 0.5245306491851807, "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_Fear/50590628a1bc7f81b3412d39ba593cf0aa2a3c1855a995ac9d3cf789541ca725.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "50a1ffc7d62b41a2a4b12f4f4ea73922cb026255cacb9975cb417b442baa14f6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "75ccc1e6f15f876361c57a74a91c3346c5daa29e89d4ae8896fd12865de3501c", "generation_seconds_batch": 20.12596257298719, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04574969410896301, "target_z": -0.4511718727163813, "ce": 6.117925643920898, "genuineness": 4.934117794036865, "identity": 0.748237133026123, "hypothesis": "La porte 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_Fear/50a1ffc7d62b41a2a4b12f4f4ea73922cb026255cacb9975cb417b442baa14f6.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "50cfad33db9bb9aab83e2b44bca668f165ae55fa803b2398077debf0b7abaa5e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "faae2b36530c9e7d09eaedd0e3bebb7156f5e099323efa291603effb484ea280", "generation_seconds_batch": 15.189673496992327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.548870801925659, "target_z": 3.640624920834553, "ce": 6.062326908111572, "genuineness": 4.042920112609863, "identity": 0.7015769481658936, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prête. Dis-moi quand tu es prête.", "wer": 0.3888888888888889, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/50cfad33db9bb9aab83e2b44bca668f165ae55fa803b2398077debf0b7abaa5e.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "515b5cd3b1cc3da28a81b57fb9856f901829a238eaa7a7f8d9ee117f288d5504", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e5612b0a0c9b4e536e7f73247ef5aefa65144a34905629aadbb16ef57e5962a3", "generation_seconds_batch": 21.566778216976672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09354197978973389, "target_z": -0.3730468788060311, "ce": 5.871703147888184, "genuineness": 4.3127899169921875, "identity": 0.48462629318237305, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/515b5cd3b1cc3da28a81b57fb9856f901829a238eaa7a7f8d9ee117f288d5504.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "51f6785fdea8db78fc22d535ae835587b7ad764e5ffbba806528e38ef888fe08", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cbe25ed28fb2132f72cef09b9c60f07e0114d5ad7f48e2f6caa57f3cd4636e25", "generation_seconds_batch": 20.90115363697987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025437980890274048, "target_z": -0.48437498173105065, "ce": 6.197352409362793, "genuineness": 4.306513786315918, "identity": 0.6898190379142761, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/51f6785fdea8db78fc22d535ae835587b7ad764e5ffbba806528e38ef888fe08.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "528cfa3d5c4b1c64886ac40586dde466609f4902e54ea6047320e4a2b30d8c49", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e37ed34442ec7bbb10207052024c3b771cf638504c28b6ba30e9ab552b70d9e5", "generation_seconds_batch": 22.23943150800187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5452327728271484, "target_z": 2.0, "ce": 5.5817952156066895, "genuineness": 4.143336772918701, "identity": 0.74770188331604, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/528cfa3d5c4b1c64886ac40586dde466609f4902e54ea6047320e4a2b30d8c49.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "52c54cb745256ffa8ad35d8c9da804a062a2f76bb2f2209b4cbeb82b8590e254", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "debc141ad192e4d58e95ec1344d6518bb766456053a76d33ec07a2ac9a78a97d", "generation_seconds_batch": 16.209546913043596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.793752670288086, "target_z": 2.4062499878207007, "ce": 5.919358730316162, "genuineness": 4.281409740447998, "identity": 0.6510340571403503, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/52c54cb745256ffa8ad35d8c9da804a062a2f76bb2f2209b4cbeb82b8590e254.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "534329d17db084cea70ff4127c75f777d10c0c3233a7596e5fd1bd979e3875eb", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9c3f94c1bc7ed9d061d3e38e3540c568e98ba99755e10ae610dc848d1c63e37c", "generation_seconds_batch": 23.016964314039797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7040884494781494, "target_z": 0.6249999512828017, "ce": 5.418970584869385, "genuineness": 4.055472373962402, "identity": 0.7219058275222778, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de. Elle était près 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_Fear/534329d17db084cea70ff4127c75f777d10c0c3233a7596e5fd1bd979e3875eb.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "53cfd0ccd9013e1c896714e3be1f7ed88f09941afa1d1b10bebb80945b78fce3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5e4f6334e0723294b725b5eea1e71590ebb5feb919ff36e39372ca392b813387", "generation_seconds_batch": 20.146079058060423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20406165719032288, "target_z": -0.19238280298492222, "ce": 6.086154937744141, "genuineness": 4.6956281661987305, "identity": 0.4909740686416626, "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_Fear/53cfd0ccd9013e1c896714e3be1f7ed88f09941afa1d1b10bebb80945b78fce3.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "5452da1436db8d331ae7f4040ddbd6de56fa0d25f8f8f58311037827e0df9764", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f20f466132225e8dc1a0477efc66dad7ee2e8d9bc06e0b52ccd3a3146de6e7e8", "generation_seconds_batch": 23.16731479507871, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8331276774406433, "target_z": 0.835937527403424, "ce": 5.736677646636963, "genuineness": 4.557555198669434, "identity": 0.6560814380645752, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/5452da1436db8d331ae7f4040ddbd6de56fa0d25f8f8f58311037827e0df9764.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "f1b84a8582d869073a37e03f34ad1b57e13676036d19fd22418940e27a260b79", "generation_seconds_batch": 16.256553636980243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07800948619842529, "target_z": -0.3984375030448249, "ce": 6.324435234069824, "genuineness": 4.111956596374512, "identity": 0.520246148109436, "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_Fear/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "549b401005bcdca1648229a7fdd58758659017a1af2c07971bbd88128e72773a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3a31758466c51920daca65be739d85c030e318d36ff729fb1da30c16e40291f8", "generation_seconds_batch": 22.002953468007036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003237396478652954, "target_z": -0.5312499878207004, "ce": 6.332377910614014, "genuineness": 4.406930446624756, "identity": 0.5497735142707825, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/549b401005bcdca1648229a7fdd58758659017a1af2c07971bbd88128e72773a.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": "549ca8594e37de2b9f90735b70e1158ba78b625c21d322d36885bd57e3a6d996", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a13bbe99846695a2ea9c237c24573e22ba9fcb52e9f9cf46b2e6009214d1929f", "generation_seconds_batch": 19.947469540056773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.061389446258545, "target_z": 2.8437499147449032, "ce": 6.0146708488464355, "genuineness": 4.174716949462891, "identity": 0.5872206687927246, "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_Fear/549ca8594e37de2b9f90735b70e1158ba78b625c21d322d36885bd57e3a6d996.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "54a28a29ea99b3db33f008c246b29acc5fb50f8c9970642c118f5a4cc813369e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8828928fdcda563b93178307caadb4893172f6d3c5538d705bad5474d353625d", "generation_seconds_batch": 21.20648012193851, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.7054443359375, "target_z": 5.5312501339722955, "ce": 5.788304805755615, "genuineness": 3.4592485427856445, "identity": 0.3713856339454651, "hypothesis": "The door is still open. I put your coat on the chair Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/54a28a29ea99b3db33f008c246b29acc5fb50f8c9970642c118f5a4cc813369e.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "5565882f84712d0e16ff917ccfd9f5348107c19750e633104c2f62dc935f811b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "760f03fe0c1f279d41b29329dccf8cf01bb53ff2395916e451cc331ac7202767", "generation_seconds_batch": 16.209546913043596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.395935535430908, "target_z": 3.3906250182689495, "ce": 5.645336627960205, "genuineness": 4.093128204345703, "identity": 0.58445143699646, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/5565882f84712d0e16ff917ccfd9f5348107c19750e633104c2f62dc935f811b.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "55930128d74e2f6a993f590a0e2640b6e4ee516d6a17cec6d18f6296d2e4f71b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a013170f5d8e2c51b9b57ab780466b26c3ea8f338c559d4f0ff3b792615155a9", "generation_seconds_batch": 23.647619134979323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1892874240875244, "target_z": 4.6874998294898065, "ce": 5.5659098625183105, "genuineness": 3.798154592514038, "identity": 0.5661078691482544, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/55930128d74e2f6a993f590a0e2640b6e4ee516d6a17cec6d18f6296d2e4f71b.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "55c08c896f16932cd3943dc589f1335256632b79b8ee3b213a2356ff8e90fa91", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "60d6c5dd47429c8d71427e08eeb7c0a35c3d1ceaaade55e5a0b689d288170cf4", "generation_seconds_batch": 21.72035479603801, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046944499015808105, "target_z": -0.4492187515224124, "ce": 6.125868320465088, "genuineness": 4.570107460021973, "identity": 0.7349869012832642, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/55c08c896f16932cd3943dc589f1335256632b79b8ee3b213a2356ff8e90fa91.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "55f43464463ab4a00e1df85d77ccbec05745f76892770c8786a540d334fbe274", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9802bfc1905f502c5df0470a4c9403d6f0f5c41ff919a7de4aa90a7d9641e715", "generation_seconds_batch": 16.272744219051674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9981184005737305, "target_z": 4.375000048717198, "ce": 5.855817794799805, "genuineness": 3.9927117824554443, "identity": 0.3986058831214905, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/55f43464463ab4a00e1df85d77ccbec05745f76892770c8786a540d334fbe274.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": "55fa0b1bf80e9ac833ce7101dda59aa2b205fb690c61e4a382d9918b6db453f2", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "99b8cf1b5e50daf3c3fc387759fb0e8957cebafd4c49e077d19eb3ed005558eb", "generation_seconds_batch": 15.641704804031178, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2680375576019287, "target_z": 1.5468751035240462, "ce": 5.871703147888184, "genuineness": 4.444586753845215, "identity": 0.6463407874107361, "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_Fear/55fa0b1bf80e9ac833ce7101dda59aa2b205fb690c61e4a382d9918b6db453f2.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "5631f37f7849fbf25f3f4cafa2a228da2ef830b305a8f2e8de03182c9df5e3ab", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "dfcbb80197a9e19ff711157b488f2c6104bea92bdabbab89964467ed975a31b9", "generation_seconds_batch": 21.873020619968884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09593158960342407, "target_z": -0.36914063641809336, "ce": 6.125868320465088, "genuineness": 4.293961524963379, "identity": 0.505475640296936, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/5631f37f7849fbf25f3f4cafa2a228da2ef830b305a8f2e8de03182c9df5e3ab.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "566786a732af62d6f50a63070b807a5c6d3e5376228163f22b6d3b6b1693d70b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0bc91801235d5a36676d1305a41f9a96def0aea7d814151628efc6305da01b8e", "generation_seconds_batch": 21.977003172039986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35415929555892944, "target_z": 0.05297849155185322, "ce": 5.871703147888184, "genuineness": 4.319066047668457, "identity": 0.6057431101799011, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/566786a732af62d6f50a63070b807a5c6d3e5376228163f22b6d3b6b1693d70b.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "567482ed28386391af424d388327da008b7b0e02317018475a6fed70dc980c87", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9600b2cfff86823a18c3b1628f32b4a375f93ca26827effb406c266873c163c5", "generation_seconds_batch": 15.308979631983675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11146408319473267, "target_z": -0.34375001217929957, "ce": 6.006728172302246, "genuineness": 4.582659721374512, "identity": 0.6877691149711609, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/567482ed28386391af424d388327da008b7b0e02317018475a6fed70dc980c87.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "5759d85761d892d08d76b6dc94c1ccf186ab508eee39dc78ad2e527588e84b2e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "cb167e7eaf7be295e6868bffb21c7d34a8eea468fc27bc32726c1db8e3076fba", "generation_seconds_batch": 22.485209417995065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1795680969953537, "target_z": -0.23242188489568089, "ce": 6.268836498260498, "genuineness": 3.986435890197754, "identity": 0.4500875473022461, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/5759d85761d892d08d76b6dc94c1ccf186ab508eee39dc78ad2e527588e84b2e.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "578b8d9ae26cfb5db6802166ed0827d9990da88189f82bae06c17e41dd256f40", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "033419f4e5e20cc15d279fdbd55f85996381f80c46e7c33a177c11043223c10a", "generation_seconds_batch": 21.30846319696866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011100292205810547, "target_z": -0.5078124847758756, "ce": 6.197352409362793, "genuineness": 4.124508857727051, "identity": 0.6825218200683594, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/578b8d9ae26cfb5db6802166ed0827d9990da88189f82bae06c17e41dd256f40.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "57a26a47ef1215e7d0a6f8bc4b7f5250339be60778c282bc8c9c6e147dc2b1f6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1c43077350d880823b31b2a54383f18216376683c002a49268070532ed0743cf", "generation_seconds_batch": 20.26379417197313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5726596713066101, "target_z": 0.41015623020863823, "ce": 6.022613525390625, "genuineness": 4.532451152801514, "identity": 0.4981958866119385, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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_Fear/57a26a47ef1215e7d0a6f8bc4b7f5250339be60778c282bc8c9c6e147dc2b1f6.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": "5830fb3395a7cad2750190b692fb0c886d83b8f32900b78290e8264a55d8206e", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6fe6ff10510b2815606a2b8f8dcb4e6fdb50a81bfe33a98ee9be30a1c625fc60", "generation_seconds_batch": 22.776459160959348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4628448486328125, "target_z": 3.500000194868793, "ce": 5.903473377227783, "genuineness": 3.7542223930358887, "identity": 0.48875945806503296, "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_Fear/5830fb3395a7cad2750190b692fb0c886d83b8f32900b78290e8264a55d8206e.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "587daa8a4199dae8a4a5eab0bea7b406ce4a3353cbb4f7dbbd083bfb9ab92268", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "973f57c3c555a653e88cfce9432eae130d5c9078c008b499c7fde5a8a786f271", "generation_seconds_batch": 22.150334041099995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.793752670288086, "target_z": 2.4062499878207007, "ce": 5.6413655281066895, "genuineness": 3.7793264389038086, "identity": 0.2887427806854248, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/587daa8a4199dae8a4a5eab0bea7b406ce4a3353cbb4f7dbbd083bfb9ab92268.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "58da8cbfdf057962dfa7448102beeef2ac89728f6274c16c1697dc94fe44f9b0", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "aaeb99ae4bc256ef2bfd8e94be702869f9a486aeebdb3a49d87ccc7a58ab66e3", "generation_seconds_batch": 22.377886679023504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.500971257686615, "target_z": 0.292968763701712, "ce": 5.967014789581299, "genuineness": 4.444586753845215, "identity": 0.58414226770401, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/58da8cbfdf057962dfa7448102beeef2ac89728f6274c16c1697dc94fe44f9b0.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "5929c078fa00b4a418724512e19b1b1619ced602a8f1134535ed3805b492c1b8", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "21eb9942da9d191d10b3e42140af5205ddf122519947e14111c57b702349b877", "generation_seconds_batch": 22.45196502597537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07442507147789001, "target_z": -0.40429686662673153, "ce": 6.141753673553467, "genuineness": 4.7332844734191895, "identity": 0.5095773935317993, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/5929c078fa00b4a418724512e19b1b1619ced602a8f1134535ed3805b492c1b8.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "593339bc7c626d35fb4c5a618d8364eb56963036f5fbf428f5cb2a12324bea37", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5644b16ff51c485aa5ed6c65d06acd8c07648b9bf21ef9df6dfd1c723657f60d", "generation_seconds_batch": 20.146079058060423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10907447338104248, "target_z": -0.3476562545672373, "ce": 6.09409761428833, "genuineness": 4.595211505889893, "identity": 0.497575581073761, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/593339bc7c626d35fb4c5a618d8364eb56963036f5fbf428f5cb2a12324bea37.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": "595ed7206bcca0d1d8787f3f92ef25e0d815f7e907b285348626c3263d845822", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f419c2edd09302f458f3edd54c4aa044098b50ab0c84ba73826ec850577b63fe", "generation_seconds_batch": 16.043422276969068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10071082413196564, "target_z": -0.3613281272836187, "ce": 5.9431867599487305, "genuineness": 4.036643981933594, "identity": 0.4028933644294739, "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_Fear/595ed7206bcca0d1d8787f3f92ef25e0d815f7e907b285348626c3263d845822.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "5986907033fa66ec49157da20e32e7d9426250053e4c9f78ac4453efad84b6bc", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "26c63018cb50aae2365db3c7a821de3ded39a303da397b941d2063b315255eef", "generation_seconds_batch": 21.395532452967018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07442507147789001, "target_z": -0.40429686662673153, "ce": 6.173524379730225, "genuineness": 4.061748504638672, "identity": 0.5583455562591553, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/5986907033fa66ec49157da20e32e7d9426250053e4c9f78ac4453efad84b6bc.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": "59b29c1f93bfd94ba20077250a163378307cc2035ab7175074c0d23f237b8d91", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b893ea2d63439eec8ac7e54c5e47566120fcc405de17eedafa6b94548bea8df", "generation_seconds_batch": 16.996140163042583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2778410017490387, "target_z": -0.07177733785065178, "ce": 5.824047088623047, "genuineness": 4.005263805389404, "identity": 0.5729885697364807, "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_Fear/59b29c1f93bfd94ba20077250a163378307cc2035ab7175074c0d23f237b8d91.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "5a20a89598f20008b435b9f336c92cf46a7a54648297814ee23977c450687525", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1328bace51c9122bd34c2f2ded26f011d1c8123d285c2aa7befe1d27528edd5d", "generation_seconds_batch": 20.908118318999186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3970767259597778, "target_z": 1.757812582210272, "ce": 5.927301406860352, "genuineness": 4.168440818786621, "identity": 0.6043264865875244, "hypothesis": "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_Fear/5a20a89598f20008b435b9f336c92cf46a7a54648297814ee23977c450687525.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": "5a3e4f9f099a36baed38210f44fb30f9bac0709027bb10fea684859ae2a254b3", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c15fb8810074aea21f6cf2b560d0530b363973b58dddec5c54dd7073be25e752", "generation_seconds_batch": 15.508048248011619, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.908454179763794, "target_z": 2.5937500121792993, "ce": 5.855817794799805, "genuineness": 4.18099308013916, "identity": 0.6608903408050537, "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_Fear/5a3e4f9f099a36baed38210f44fb30f9bac0709027bb10fea684859ae2a254b3.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": "5a4981aa510bf9272c9dc2fcf052fe46659991407f2260e60a6b4931834cf9c3", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4d16d569f753b1e404b6f3f7aff1f76416ca95ccff36483313d83074fa0984bd", "generation_seconds_batch": 15.05554748501163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2238831520080566, "target_z": 3.109374786862258, "ce": 6.268836498260498, "genuineness": 3.512594699859619, "identity": 0.7510849833488464, "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_Fear/5a4981aa510bf9272c9dc2fcf052fe46659991407f2260e60a6b4931834cf9c3.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "5a9a6f46febea8813a56ee576ac14bffad5b878e2be0d9e0f9509056ebad9b1a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2e1958744758dd96f58d63cc9dfdf8f4d9a12740a6b659b05532d0d9f4feb86a", "generation_seconds_batch": 21.940121141029522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35699698328971863, "target_z": 0.05761719701507778, "ce": 6.1020402908325195, "genuineness": 3.9550557136535645, "identity": 0.31398606300354004, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/5a9a6f46febea8813a56ee576ac14bffad5b878e2be0d9e0f9509056ebad9b1a.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "5ac5eefb11addd5c75abc6ae3572b51e5a3da0e133f92c4946793eda7813bba4", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4aaf2f17bb60462e8b12e387d6d64215f66b5bfdff0d7f66b1126262303753ff", "generation_seconds_batch": 20.03522222302854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.701698899269104, "target_z": 0.6210938063292605, "ce": 5.474569320678711, "genuineness": 4.15588903427124, "identity": 0.6934110522270203, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt, Louise. Dis-moi quand tu es prêt.", "wer": 0.3888888888888889, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/5ac5eefb11addd5c75abc6ae3572b51e5a3da0e133f92c4946793eda7813bba4.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "5acfd7b8367ef75628efd3ffbd6c5904b59dc1d6f2cb63eae42911f07c973c89", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "875056eb257bc7df4380d67e5d69ecc805abe25d1af545911512bedf85e0e211", "generation_seconds_batch": 20.126751984935254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1091818809509277, "target_z": 2.9218751522412445, "ce": 5.792276382446289, "genuineness": 4.149612903594971, "identity": 0.4752703011035919, "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_Fear/5acfd7b8367ef75628efd3ffbd6c5904b59dc1d6f2cb63eae42911f07c973c89.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "5b3130a4dc343e62f55ebe954b05fd5313273446a667b7d8e7f11eeca08fea84", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6e5d49b4f15e41f94cf992f852a0ce396dd6bff27c411de4a509d9aed8a1f33d", "generation_seconds_batch": 22.77006153203547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1706070452928543, "target_z": -0.24707031820904668, "ce": 5.903473377227783, "genuineness": 4.582659721374512, "identity": 0.8409830331802368, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/5b3130a4dc343e62f55ebe954b05fd5313273446a667b7d8e7f11eeca08fea84.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "5b84538c71861566a4ef208d342b923c72a4a4fa6357b8973410293ba89ee299", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f279dc86b1ec7afc51eea27f32aaed4ba7b87029ff6fc7011bcba36280afffa8", "generation_seconds_batch": 20.657649794011377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7172850370407104, "target_z": 2.2812500365378985, "ce": 5.601652145385742, "genuineness": 4.331617832183838, "identity": 0.4006740152835846, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/5b84538c71861566a4ef208d342b923c72a4a4fa6357b8973410293ba89ee299.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "5ba2bd65bb30fcd2d64946321c8488261d0787ece119cffef554a5c482b2e2af", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3359e08ee80779599bcc918cf6a127beb8d8b3d496e37cdd3ad1731c593eecb3", "generation_seconds_batch": 19.14738253399264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024243175983428955, "target_z": -0.48632810292501955, "ce": 6.006728172302246, "genuineness": 4.18099308013916, "identity": 0.3799511790275574, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/5ba2bd65bb30fcd2d64946321c8488261d0787ece119cffef554a5c482b2e2af.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "5cd25fd04a13d3bcfa3eb766dfc1c6b1281ffa58c4aecb3ddb5c00100baaf465", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a266abd99b3094c567037b9422250df89311596440e7f0843b26a662338a49cf", "generation_seconds_batch": 20.659014888107777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0745859146118164, "target_z": 4.499999805131207, "ce": 6.1020402908325195, "genuineness": 3.616149425506592, "identity": 0.5334134101867676, "hypothesis": "The 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_Fear/5cd25fd04a13d3bcfa3eb766dfc1c6b1281ffa58c4aecb3ddb5c00100baaf465.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": "5cf9d7733ef08c12d687f863d13ff18a4036d6753ef2e7f370c643089d9e5a01", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6c53acb6b2d3ef6b0ca76b259d26f89aa6ce8a5aea9fb1a753b5bec4100993bf", "generation_seconds_batch": 22.012183724087663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9753633737564087, "target_z": 2.7031249939103503, "ce": 5.8875885009765625, "genuineness": 3.9425034523010254, "identity": 0.6935482025146484, "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_Fear/5cf9d7733ef08c12d687f863d13ff18a4036d6753ef2e7f370c643089d9e5a01.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "5de67aa0e7983ca75a0fbe98a2cb6561d61dd0b9dbac506b5c24607d1b728935", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1ce781ed09882de626e72e2c75e8f64377bd819aab9c85b0b175343bdc6b7083", "generation_seconds_batch": 16.85675903200172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03499642014503479, "target_z": -0.46875001217929957, "ce": 5.95112943649292, "genuineness": 4.469690799713135, "identity": 0.693175733089447, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/5de67aa0e7983ca75a0fbe98a2cb6561d61dd0b9dbac506b5c24607d1b728935.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": "5e0ae03da2b6ded8c996fd43eea00aaa4fb0d405bc8cf59d73cc64c44d13d960", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "17be18c57d96b4b2cb4aaa3adcbc43143d24438b285c42bc34c2d87dccf6284d", "generation_seconds_batch": 16.672528057009913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6586858034133911, "target_z": 0.5507812484775876, "ce": 6.133810997009277, "genuineness": 4.457139015197754, "identity": 0.6982989311218262, "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_Fear/5e0ae03da2b6ded8c996fd43eea00aaa4fb0d405bc8cf59d73cc64c44d13d960.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "81a873fd651bbff5c9b3805366a4d26c7a29f262ccd44bf12db2e16d496a221e", "generation_seconds_batch": 15.791826182045043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0624769926071167, "target_z": -0.4238281272836187, "ce": 6.117925643920898, "genuineness": 4.331617832183838, "identity": 0.6856199502944946, "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_Fear/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.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": "5e7c2f02c1863b265bd1369f519e9f8bef195c14f33bddb29b32f5f326a2eac5", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "09c48e941f4722072231ceea415a7e51207998d54724084659390b9c6ea75187", "generation_seconds_batch": 22.012183724087663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6778026819229126, "target_z": 0.5820311875810897, "ce": 5.704906940460205, "genuineness": 3.8671910762786865, "identity": 0.5114599466323853, "hypothesis": "Jemand hatte den kleinen blauen Stuhl umgestellt. Er stand hier, neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "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_Fear/5e7c2f02c1863b265bd1369f519e9f8bef195c14f33bddb29b32f5f326a2eac5.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "5ec622eb8793f3c6c2c409354caf0f3b54142a3d305175f7cb4ac2f0be048bb3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3a50514d5820e1909f00b1602b5eb49c7998f0a9f30703b59ccacfa5ab959b10", "generation_seconds_batch": 20.668674588901922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03499642014503479, "target_z": -0.46875001217929957, "ce": 6.078212261199951, "genuineness": 4.720732688903809, "identity": 0.5820903778076172, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/5ec622eb8793f3c6c2c409354caf0f3b54142a3d305175f7cb4ac2f0be048bb3.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "5ec66b6a7fe4ee367f67961925ca0942df49b8f54932f1a8cad37f2519107247", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "92fd544ffb4002cbd4d006ec7ea5c514b7245142d017a4baddec4a64dc6d82d6", "generation_seconds_batch": 16.365282217040658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0039314329624176025, "target_z": -0.5195312606568872, "ce": 6.3641486167907715, "genuineness": 4.532451152801514, "identity": 0.39430487155914307, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/5ec66b6a7fe4ee367f67961925ca0942df49b8f54932f1a8cad37f2519107247.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "5f0ac316092bf347d5a2721a69a88e1df034842c9f0ca01ff85f3fd166f6c66e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7c4643a3eb2e3f6569f0f49a177c7274bfaaecf229cc167f52e6ee6fc85cbb8a", "generation_seconds_batch": 22.020389165030792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6981680393218994, "target_z": 2.2499999025656034, "ce": 5.700935363769531, "genuineness": 3.9299514293670654, "identity": 0.4204563498497009, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime, ¿cuándo estás listo?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/5f0ac316092bf347d5a2721a69a88e1df034842c9f0ca01ff85f3fd166f6c66e.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "5f81e4c949f9321efb23b5ad8c167f9c938f3cb88d6f057ffc7fc2a96e07f330", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9651f08e6b25e9e69cf01a9e6e81f48641b1b033019f9e650c21016e25624135", "generation_seconds_batch": 15.141561339027248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9526084065437317, "target_z": 1.0312500365378987, "ce": 6.133810997009277, "genuineness": 4.362998008728027, "identity": 0.5246585607528687, "hypothesis": "He encontrado la. 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_Fear/5f81e4c949f9321efb23b5ad8c167f9c938f3cb88d6f057ffc7fc2a96e07f330.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "5fb418226800678496760174f62f8880d7602dc4bac83499c75919c8c78e2f42", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d1bb2289f8011a34b308afd3a611a1e41acc451197f29ec6e28b907b4fb8ceb0", "generation_seconds_batch": 15.454123741015792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.621700406074524, "target_z": 2.1249999512828017, "ce": 5.804190158843994, "genuineness": 3.9801597595214844, "identity": 0.39465877413749695, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/5fb418226800678496760174f62f8880d7602dc4bac83499c75919c8c78e2f42.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": "5fe360e954cc040b4a6cf545c7c7fdd92adb080cc390ab262e0081a4ab572f58", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d48493dfd7ead5eccba245587c3f5858b43e3826620b9efdc18a4f0df41a3bb9", "generation_seconds_batch": 21.896005881018937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0338551998138428, "target_z": 1.1640623751621795, "ce": 5.629451274871826, "genuineness": 3.578493118286133, "identity": 0.518818199634552, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder. Tot aan het kleine... aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.19047619047619047, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/5fe360e954cc040b4a6cf545c7c7fdd92adb080cc390ab262e0081a4ab572f58.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "60266e3c65edd702be1a6b6f19d49179151699683d03df3afa2312330caae2fb", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1f0fdef644aec4c7739137f190c45220876673219cf70b6e9a1c06f6593d8327", "generation_seconds_batch": 20.580970279988833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.395935535430908, "target_z": 3.3906250182689495, "ce": 5.824047088623047, "genuineness": 3.452972412109375, "identity": 0.6412726640701294, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/60266e3c65edd702be1a6b6f19d49179151699683d03df3afa2312330caae2fb.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "61754b772368e0caf9ee60d63f7b8b590b9050d3995384eaf44516ae8eb12b4a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b59c08d681d0d69e75df267e0df025542208c4a222643fc218a2399e0cf496e4", "generation_seconds_batch": 21.86353756301105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9598846435546875, "target_z": 4.3125001705101935, "ce": 5.601652145385742, "genuineness": 3.9299514293670654, "identity": 0.5296835899353027, "hypothesis": "La porte la porte est encore 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_Fear/61754b772368e0caf9ee60d63f7b8b590b9050d3995384eaf44516ae8eb12b4a.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "6177409d35995899fdec687c161c141be2fd27b3e1a7521dc39bdf9f97562ce8", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "eb7adcabf1901b9d104910155ddd13e74110481898b63fc9c6aca8a630241930", "generation_seconds_batch": 21.654425497050397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7459603548049927, "target_z": 2.328124945193152, "ce": 5.824047088623047, "genuineness": 3.7416701316833496, "identity": 0.3426501154899597, "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_Fear/6177409d35995899fdec687c161c141be2fd27b3e1a7521dc39bdf9f97562ce8.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "619cb060b2f54dc89ed9273a3cd636495b9e54d12bf66ea4c911121b896e6e3f", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "79d3179c7264d57bfb9561e0eb65a945276e681e08da0fad52584f4f68afce3c", "generation_seconds_batch": 19.903555126977153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.526115894317627, "target_z": 1.9687500608964978, "ce": 5.25614595413208, "genuineness": 3.9173994064331055, "identity": 0.5891605615615845, "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_Fear/619cb060b2f54dc89ed9273a3cd636495b9e54d12bf66ea4c911121b896e6e3f.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "61a05567e4fb941c58624e65b214dcfba3a4d84c30d0814580a0697d775a16a8", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5e36aa613ab4227bc1137d1714a443bab63b60cbbbec23619c36e8ae6deef77a", "generation_seconds_batch": 22.06744200293906, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0481393039226532, "target_z": -0.4472656303284436, "ce": 6.062326908111572, "genuineness": 4.645420074462891, "identity": 0.7768962383270264, "hypothesis": "J'ai trouvé la petite boîte elle était près de la de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/61a05567e4fb941c58624e65b214dcfba3a4d84c30d0814580a0697d775a16a8.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "61cba9d01501518a295790883bf8d84455a08d7e9014d2e996e65f0e19c38e09", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "11709f4a5488c28761dc97598b43fc99eda62aa475ca1acd696616cba720a5e2", "generation_seconds_batch": 20.87098663195502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.043413758277893, "target_z": 1.1796875395827235, "ce": 5.871703147888184, "genuineness": 3.6914620399475098, "identity": 0.4673134982585907, "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_Fear/61cba9d01501518a295790883bf8d84455a08d7e9014d2e996e65f0e19c38e09.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "621f886dc5d0852a0b584ef8fc66cf6927a5779e6c73fa3cfdd8e6f15ff4a25a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a5c5874d5c6a650da7e1e058ac3b94c399053ef7ecc3c22445eb63fe50718981", "generation_seconds_batch": 15.58970342995599, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021853536367416382, "target_z": -0.49023439403015556, "ce": 6.292664527893066, "genuineness": 4.080576419830322, "identity": 0.5890874266624451, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/621f886dc5d0852a0b584ef8fc66cf6927a5779e6c73fa3cfdd8e6f15ff4a25a.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": "625af255e1c8104896101ec0132ddaf7f2364f2ebfcab2f4d0835e5b1ca86f6c", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "284cb236b5519a460ed2aca2ff46c0a3af584bbbffb0e8de1dea7ccc02803239", "generation_seconds_batch": 22.155466479016468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1066848635673523, "target_z": -0.3515624969551751, "ce": 5.796247482299805, "genuineness": 3.9299514293670654, "identity": 0.49443918466567993, "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_Fear/625af255e1c8104896101ec0132ddaf7f2364f2ebfcab2f4d0835e5b1ca86f6c.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "62fd4e4d5cd72738097ab93b6d3c9ce20c30d49498562c2cf2754505c505834a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e3c5f1a9a66843f65614f4bc39456fb4325289f3d5fdd0341ca51474fbe1bdfd", "generation_seconds_batch": 23.469891625922173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13894465565681458, "target_z": -0.2988281272836187, "ce": 6.0305562019348145, "genuineness": 4.319066047668457, "identity": 0.794437050819397, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/62fd4e4d5cd72738097ab93b6d3c9ce20c30d49498562c2cf2754505c505834a.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "64989a84cdcd23f3b33137305d8f90c567d492bded2337a8be1e7927edf2d990", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "87a1a648ff8a647108d012d79f3ea41e17c5eed944cdfa0a11cd21da3d31f7f8", "generation_seconds_batch": 23.590407209005207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015879511833190918, "target_z": -0.5, "ce": 6.3641486167907715, "genuineness": 4.532451152801514, "identity": 0.43428584933280945, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/64989a84cdcd23f3b33137305d8f90c567d492bded2337a8be1e7927edf2d990.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": "64a0e325dc8187323e821e918f3151362ab1e6076b74c8ba2a8d1f96c983eb60", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a14be7464a09124f1520e5b0532ef9ccc668f463b29b6319a3f023f9eda8794b", "generation_seconds_batch": 17.66154548607301, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1581151485443115, "target_z": 1.3671873690725298, "ce": 5.617537498474121, "genuineness": 4.15588903427124, "identity": 0.7608742713928223, "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_Fear/64a0e325dc8187323e821e918f3151362ab1e6076b74c8ba2a8d1f96c983eb60.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "64c917ffe3803a314b3572f7de9d0bb81e09f576c491311145a0de0e09c11613", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "88b9636a8ccfdbc48c74f4b66f6fafb90106e0f7d04033e4086c52449683fa19", "generation_seconds_batch": 22.65324461599812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1103229522705078, "target_z": 1.2890625213137743, "ce": 6.038498878479004, "genuineness": 4.093128204345703, "identity": 0.6634989976882935, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/64c917ffe3803a314b3572f7de9d0bb81e09f576c491311145a0de0e09c11613.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "6556ef1d92434dcc408eca7378b51b36b43f2233d24fa20d13e3af4763b3ea2e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "f4600c46beb7bf14c3a975aac1ca25c47da04c08f77b205fd7c34b74def1eb03", "generation_seconds_batch": 20.77032871998381, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.673130750656128, "target_z": 3.8437499147449032, "ce": 5.268059730529785, "genuineness": 3.9048471450805664, "identity": 0.7366462349891663, "hypothesis": "J'ai Drusse. J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/6556ef1d92434dcc408eca7378b51b36b43f2233d24fa20d13e3af4763b3ea2e.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": "65a3dde82ef1d6e9ad332ce3de2b18311a124b20b82a8b119f5d88721cf061d5", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c97e42b9d83bb5bd65892a586bce1d58396a3e6ed9abd9531829481cd7e0ed74", "generation_seconds_batch": 15.710691784974188, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1652304232120514, "target_z": -0.25585936358190664, "ce": 5.847874641418457, "genuineness": 4.20609712600708, "identity": 0.22337232530117035, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplacht. 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_Fear/65a3dde82ef1d6e9ad332ce3de2b18311a124b20b82a8b119f5d88721cf061d5.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "65a810bc5cd19622027a28435a4bbbc71be4f92a97adea9afa52790763a83b23", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c1360eb684016863c27d395a0d56b39380161f37b2ebc0ca7d6ee19f680ae3d3", "generation_seconds_batch": 20.966969914967194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1992824226617813, "target_z": -0.2001953121193969, "ce": 5.8875885009765625, "genuineness": 4.105680465698242, "identity": 0.400900661945343, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/65a810bc5cd19622027a28435a4bbbc71be4f92a97adea9afa52790763a83b23.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "66de8accf487e2cef86c346e416f770d3983ee6ff4886655921d2cf2cffb460b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2ba16e78201c9ed1aeb90615d37858bb42e8473f1ef4a4021467c73fb47c17fa", "generation_seconds_batch": 15.57541972398758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1510536670684814, "target_z": 4.624999951282802, "ce": 5.871703147888184, "genuineness": 3.5565271377563477, "identity": 0.49248093366622925, "hypothesis": "The 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_Fear/66de8accf487e2cef86c346e416f770d3983ee6ff4886655921d2cf2cffb460b.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "673fca78e4ec1cd84991288f0dc02f2257215213b92732b4199ecc3f90b0f257", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "49c9821425ae4f16358c3707ce2382ab8696198e674e339444f7bac164eee499", "generation_seconds_batch": 15.784480702015571, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5393123626708984, "target_z": 3.6249999512828017, "ce": 5.661221981048584, "genuineness": 4.017816066741943, "identity": 0.5539125204086304, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/673fca78e4ec1cd84991288f0dc02f2257215213b92732b4199ecc3f90b0f257.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "676892d98a2a718786e222acc700125a520b934569dd41e00073b0dbeeb30775", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "152ac28601c0d5391482123af516f311d19ddb99a7b3ed4de06b5087cad2aa5d", "generation_seconds_batch": 21.426383660989814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3206090927124023, "target_z": 1.6328126309274702, "ce": 5.649308204650879, "genuineness": 4.356721878051758, "identity": 0.5324670076370239, "hypothesis": "La porte est encore ouverte j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/676892d98a2a718786e222acc700125a520b934569dd41e00073b0dbeeb30775.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "67839985833bf73f661c3afc9d7c391cea5beb422c7aec8850a10199677ee0df", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "74bcf04c5be075022691c88b545764efd45d054e79db3cd7ac2fb2317fe80a1c", "generation_seconds_batch": 22.80758644803427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013489902019500732, "target_z": -0.5039062423879378, "ce": 6.268836498260498, "genuineness": 4.632867813110352, "identity": 0.5641576647758484, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/67839985833bf73f661c3afc9d7c391cea5beb422c7aec8850a10199677ee0df.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "67d281a0fb51f2034640fd041907cb5e4ec88902a9e5bcbc82b853aa79093b4e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a05ba05401d2fb302909cb8441c83e9217ab94e3e446115b745303279f6c3d8d", "generation_seconds_batch": 19.809283465030603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5726596713066101, "target_z": 0.41015623020863823, "ce": 5.752562999725342, "genuineness": 4.13078498840332, "identity": 0.4937123656272888, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/67d281a0fb51f2034640fd041907cb5e4ec88902a9e5bcbc82b853aa79093b4e.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": "680a25d61b5d3ffb371e2d4a45cb87d6da56ab3019225f71db9451e27c486581", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "500b72235b525fbc9f9928359c1fe689e87807e577a83eedb2ee9c7e8486352a", "generation_seconds_batch": 18.08747296803631, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.13785719871521, "target_z": 2.9687500608964976, "ce": 6.038498878479004, "genuineness": 4.080576419830322, "identity": 0.5207644104957581, "hypothesis": "Die Schlüsse liegen auf dem Küchentisch. Ich suchte in der Schublade dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "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_Fear/680a25d61b5d3ffb371e2d4a45cb87d6da56ab3019225f71db9451e27c486581.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": "690c1597ceec167d04df937525a95fa486bf4c9f57f7415b7119bf4ec439c579", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "365315d68fed685c1cd2cb1c4f25731ae7d869984b9f8745c1daecf624a0774e", "generation_seconds_batch": 21.14904306700919, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8451831340789795, "target_z": 4.125000146151595, "ce": 6.086154937744141, "genuineness": 3.5094566345214844, "identity": 0.5732576847076416, "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_Fear/690c1597ceec167d04df937525a95fa486bf4c9f57f7415b7119bf4ec439c579.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "a8be5b1d6a8983b5becbb9aa0d381a9fad33e5aba3554c3914668e4c446c1d05", "generation_seconds_batch": 14.752619983046316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04336008429527283, "target_z": -0.4550781151043191, "ce": 6.3641486167907715, "genuineness": 4.017816066741943, "identity": 0.39642590284347534, "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_Fear/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "6b0f55cdb2af7fdc0996ae05b6df7b9c53d6e3e3333f363aefa26492f3691856", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "017cff1924e66dc326a56f381922647c508822becb2f5fd52afe20ebe538b363", "generation_seconds_batch": 20.542312616016716, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00562700629234314, "target_z": -0.5351562302086382, "ce": 6.284721851348877, "genuineness": 4.394378662109375, "identity": 0.3341582715511322, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/6b0f55cdb2af7fdc0996ae05b6df7b9c53d6e3e3333f363aefa26492f3691856.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "6b1267a6fac11379e2b38b8e00124fa60815738a088af961038839f40eddacdd", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "432003d7a3cfff6fcafa6244e3e89cb21283edb006a6b658aa1c504ebbeedbbe", "generation_seconds_batch": 21.615502179018222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2811267077922821, "target_z": -0.0664062667465369, "ce": 5.9431867599487305, "genuineness": 4.394378662109375, "identity": 0.5783175230026245, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/6b1267a6fac11379e2b38b8e00124fa60815738a088af961038839f40eddacdd.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": "6b4c5bd9820d7e16fb0a1670408d3f22a131b8c332531723653d980be6675183", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7ba954050129a67f901f2d6614d99b0bdaf6af4028509fadf63a4722359af353", "generation_seconds_batch": 22.776459160959348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8033111095428467, "target_z": 2.4218749573724514, "ce": 5.927301406860352, "genuineness": 3.8546390533447266, "identity": 0.5287996530532837, "hypothesis": "The keys are on the kitchen table. I check the drawer, then look beside the window. Take them with you when you leave.", "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_Fear/6b4c5bd9820d7e16fb0a1670408d3f22a131b8c332531723653d980be6675183.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "6b65cd3f172190c1ab787641a79bae500531c5c53fa699a9408cfed56f44e4a8", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "37eb3abf1a65cc12f8c38a03b7d1109e73e13a01700a725a69f8f5c6e42b0b66", "generation_seconds_batch": 20.82196119299624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.510637044906616, "target_z": 3.5781250426275486, "ce": 5.839932441711426, "genuineness": 3.5816311836242676, "identity": 0.20753106474876404, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het... Het stond naast het oude raam. We kunnen het samenheen kijken.", "wer": 0.3888888888888889, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/6b65cd3f172190c1ab787641a79bae500531c5c53fa699a9408cfed56f44e4a8.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "d695803e208faa7d0f22036f248931eb2bd712042d60d84fc861a6949ba46b46", "generation_seconds_batch": 13.829734422964975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05172371864318848, "target_z": -0.4414062667465369, "ce": 6.165581703186035, "genuineness": 4.494794845581055, "identity": 0.595964789390564, "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_Fear/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "6b999fd5159c56810438d032d04260d54e2ff28a8245e5ce5e374a0a65df7984", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "80ed8f0ad70ead280e44a889c9906ee6120cfa522e05c6b728ec71f9e16946ca", "generation_seconds_batch": 15.103446474997327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08517833054065704, "target_z": -0.3867187515224124, "ce": 5.736677646636963, "genuineness": 4.105680465698242, "identity": 0.11957534402608871, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/6b999fd5159c56810438d032d04260d54e2ff28a8245e5ce5e374a0a65df7984.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "6bf482e9fb5cae6fa76210699dffb723557805a50b66dafc07017fe6e03f5b9a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "97044d200a4e522cd154dab6c534fa6ccc616da685c7b438a6dea70762e4d55e", "generation_seconds_batch": 21.158045938936993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.908454179763794, "target_z": 2.5937500121792993, "ce": 5.974957466125488, "genuineness": 4.143336772918701, "identity": 0.6234920024871826, "hypothesis": "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_Fear/6bf482e9fb5cae6fa76210699dffb723557805a50b66dafc07017fe6e03f5b9a.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "6c305e71576a95c904adebc5e6d3744a99b490c17bb1afa888b5c92e69c41fd4", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f994e1cc75103d535e7190cec5e2a28b9f017e6188de87cc090cefb4cee1f378", "generation_seconds_batch": 21.738011996028945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.443727731704712, "target_z": 3.468749866027705, "ce": 5.95112943649292, "genuineness": 4.105680465698242, "identity": 0.5798107385635376, "hypothesis": "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_Fear/6c305e71576a95c904adebc5e6d3744a99b490c17bb1afa888b5c92e69c41fd4.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "6c4c0ada3a7df9d5138f684ef8f54a53c18d19e525f86192ac9b2b299584078b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9ed0ed14f6f8223fe30f48a07705fc48585b8a00210e4be86ea7627408d3de62", "generation_seconds_batch": 21.857322057010606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1510536670684814, "target_z": 4.624999951282802, "ce": 5.327630043029785, "genuineness": 3.418454170227051, "identity": 0.030867209658026695, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen samen inkijken.", "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_Fear/6c4c0ada3a7df9d5138f684ef8f54a53c18d19e525f86192ac9b2b299584078b.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "6c9f570b29cef878b562e0f1fb56ec593f761b374da8f540279e85f08287af0e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "47eeb586c7568ece8db62dcc95617ea641cfb98dec4222b8f047ce9358902273", "generation_seconds_batch": 20.496791540062986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3194680213928223, "target_z": 3.2656252618549404, "ce": 5.530168056488037, "genuineness": 3.9173994064331055, "identity": 0.4806676506996155, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/6c9f570b29cef878b562e0f1fb56ec593f761b374da8f540279e85f08287af0e.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "6ca66a79801e8eb987f2002da5cbff53c70d2a673d3ffd8fd51630ad94dfd91f", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0f1848ff63d39aaef691ba25f068577fa1ea7f6f17aab5058917c6030e0e7fbe", "generation_seconds_batch": 20.644085936946794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6025835275650024, "target_z": 2.0937500121792993, "ce": 5.744620323181152, "genuineness": 4.432034492492676, "identity": 0.4711179733276367, "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_Fear/6ca66a79801e8eb987f2002da5cbff53c70d2a673d3ffd8fd51630ad94dfd91f.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "6cb8615cd91eeddf708956018cd25ba1230af785307f27f9d0263a47385ae4d3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "88998edae4458a28583f5389b249a5b77e0baf9632e78687244532db71d1ef2e", "generation_seconds_batch": 21.459582892013714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018269121646881104, "target_z": -0.4960937576120622, "ce": 6.157639026641846, "genuineness": 4.65797233581543, "identity": 0.7457037568092346, "hypothesis": "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_Fear/6cb8615cd91eeddf708956018cd25ba1230af785307f27f9d0263a47385ae4d3.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "6e2e2e2f09768de92cab60e4fdb66634c81ac271c4939c0e32934bd7f40fd06e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "170e35e36fa9788753a9b1713ca8c4d96cde9a66b8dcc1e60f7e63fe9bf644ba", "generation_seconds_batch": 21.952718800050206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11624331772327423, "target_z": -0.3359375030448249, "ce": 5.792276382446289, "genuineness": 4.457139015197754, "identity": 0.38490980863571167, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/6e2e2e2f09768de92cab60e4fdb66634c81ac271c4939c0e32934bd7f40fd06e.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "6e9cb2e8cdda2b10358b090e2af560f01e189741b7d1d5cdd791e0abad6dd95c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0bfd8acbaa8bc382aee421250f197bfbe049a3ed5a518426f9bf4e27b31d6f85", "generation_seconds_batch": 21.259963909047656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8128695487976074, "target_z": 2.4374999269242026, "ce": 5.895530700683594, "genuineness": 3.7165660858154297, "identity": 0.5137202143669128, "hypothesis": "I found the little box. It 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_Fear/6e9cb2e8cdda2b10358b090e2af560f01e189741b7d1d5cdd791e0abad6dd95c.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "6f1d7b3e9d04bd608cde66728e0e14e32bf2d6b6ec0f7eb963da1d5f2565786b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8d19b2b01f1704319de4e99affe053ed7c908fa1cd709a9c82de2f71c18a266f", "generation_seconds_batch": 21.828597442014143, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31600016355514526, "target_z": -0.009399398790800166, "ce": 6.046441555023193, "genuineness": 4.2249250411987305, "identity": 0.6731889247894287, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/6f1d7b3e9d04bd608cde66728e0e14e32bf2d6b6ec0f7eb963da1d5f2565786b.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": "6f6cb95a9c0e8fdd96fc84379885bf7f1fb475c4061c106be030f1017374def1", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e05e07932af54790a5eb167b454af48f7344091ad0ada4d288ca33457051140f", "generation_seconds_batch": 24.08471425692551, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9072057008743286, "target_z": 0.957031236298288, "ce": 5.689021587371826, "genuineness": 3.8546390533447266, "identity": 0.46695074439048767, "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_Fear/6f6cb95a9c0e8fdd96fc84379885bf7f1fb475c4061c106be030f1017374def1.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "6f8d71316a2a6585e711d92a1c4345b7b23a0c2aa155ed0dd33b849d32d0bb5e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2b58373beacf9b9195cf78ea4199926e298f3e008d3a663822e5c671ce454def", "generation_seconds_batch": 20.601083906018175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0363521575927734, "target_z": 4.437499926924203, "ce": 5.4825119972229, "genuineness": 3.7416701316833496, "identity": 0.5887213349342346, "hypothesis": "Die Tür, die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/6f8d71316a2a6585e711d92a1c4345b7b23a0c2aa155ed0dd33b849d32d0bb5e.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "6f8eb0f20b9285b2b252411e95e4707a97d3c63e002ba9d2827d726f356c9cc6", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b1aaaecc401437996b6bfce889dafc4ffb59aacc8d44269e3dfb8c1fdf87d35f", "generation_seconds_batch": 15.745606953045353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006321042776107788, "target_z": -0.5156250182689494, "ce": 6.125868320465088, "genuineness": 4.632867813110352, "identity": 0.7507969737052917, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/6f8eb0f20b9285b2b252411e95e4707a97d3c63e002ba9d2827d726f356c9cc6.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "6fa32ca24d643fa17d10ca731399eb8fd4e78cc36dcf741851ed3f17df081330", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3a45151cf7e4e5bf6cbd1ac80db99dd5f04fa5fc84c978bc842f8c601c861b9e", "generation_seconds_batch": 22.44767971104011, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0008477866649627686, "target_z": -0.5273437454327626, "ce": 6.117925643920898, "genuineness": 4.055472373962402, "identity": 0.5273531675338745, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/6fa32ca24d643fa17d10ca731399eb8fd4e78cc36dcf741851ed3f17df081330.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "7021bdd2cb4a39cd2dfde5348919b5247399c01bf714ade7365d2ec7c68bf376", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fe228921eccf93d26b0fe6064228aa773e21b1b288241b819260f7060e16bb8f", "generation_seconds_batch": 21.310944195953198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.010406255722045898, "target_z": -0.542968763701712, "ce": 6.372091293334961, "genuineness": 4.607763767242432, "identity": 0.642892062664032, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7021bdd2cb4a39cd2dfde5348919b5247399c01bf714ade7365d2ec7c68bf376.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "7062c038a7af3e489c25374bcd884db978ce20a2d816f53a8fbe05b38e986f1a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "17619a055806ed852fa5cd12a9ee09799183127f24d8dc1ef92c9528829251f6", "generation_seconds_batch": 21.89527939702384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1066848635673523, "target_z": -0.3515624969551751, "ce": 5.982900142669678, "genuineness": 4.400654315948486, "identity": 0.810576319694519, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7062c038a7af3e489c25374bcd884db978ce20a2d816f53a8fbe05b38e986f1a.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "70c58a5ebeccb9f7a77b2bc19e3fb77647e2adaff82887b6013373fbe111eaed", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a428a31d36f62d2193c5b3fcb24c5828aed4b64a8e273031eb8e2e69283351a2", "generation_seconds_batch": 23.03132244409062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19032137095928192, "target_z": -0.21484374543276266, "ce": 6.157639026641846, "genuineness": 4.833701133728027, "identity": 0.7148786783218384, "hypothesis": "Die Tür ist noch offen. Ich habe dein Mantel auf den auf den Stuhl gelegt. 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_Fear/70c58a5ebeccb9f7a77b2bc19e3fb77647e2adaff82887b6013373fbe111eaed.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "717975175dab8f0027732a9cad33ad1d09ea60abb052c1782f78302939e839c2", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "dcd381e24572f3ccbce2de714902025eb22aad32292e067dbfb060c534c5b17a", "generation_seconds_batch": 23.012750147026964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2919336557388306, "target_z": 1.585937527403424, "ce": 5.831989288330078, "genuineness": 3.848362922668457, "identity": 0.29346445202827454, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je 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_Fear/717975175dab8f0027732a9cad33ad1d09ea60abb052c1782f78302939e839c2.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "71a8c1ae9b0ef0aa55015251f369878219888fff2bad033e0edd685c224392fb", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "de0d5bcfa39c232195452a92db1822d19c71a6ff2fc9a94b30c3c52abc5d59e1", "generation_seconds_batch": 21.158045938936993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.640817403793335, "target_z": 2.1562500852550968, "ce": 5.804190158843994, "genuineness": 4.281409740447998, "identity": 0.4211026430130005, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. Vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/71a8c1ae9b0ef0aa55015251f369878219888fff2bad033e0edd685c224392fb.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": "72dc791a3bd569a7ce1bd2d937a48cf7fe6de1d7bf7ef977cfeadb48d470c6da", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7a427ba3dc2f7c86389e6abae9567c1b83ec14397c98967bebddb98561f7e5e1", "generation_seconds_batch": 13.719729471951723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07323026657104492, "target_z": -0.40624998782070043, "ce": 6.205295085906982, "genuineness": 3.835810661315918, "identity": 0.4726053774356842, "hypothesis": "Someone moved the little blue chair. It used 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_Fear/72dc791a3bd569a7ce1bd2d937a48cf7fe6de1d7bf7ef977cfeadb48d470c6da.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "73166ca7870c2b721139fe8afe4913d153a3364951581c77213fb588ac534671", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "540f67f2bcfd54bda3f371c924ba2812632fb88bd9e2dc486423009f51439c7d", "generation_seconds_batch": 21.483075611991808, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.663572311401367, "target_z": 3.828124945193152, "ce": 5.780362129211426, "genuineness": 3.8546390533447266, "identity": 0.6217446327209473, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Pierta y que sea promoción, sobre todo. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.9333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/73166ca7870c2b721139fe8afe4913d153a3364951581c77213fb588ac534671.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "7327da152dc243b1970e9abd3983360d6203741604e96941445eb67de94f9a38", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ad8347de9b717a1b424ad91b43d0f54efcfc6861eff8127b7ab7e9a244d13608", "generation_seconds_batch": 20.130269059096463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1353602409362793, "target_z": -0.3046874908655253, "ce": 6.133810997009277, "genuineness": 4.432034492492676, "identity": 0.5881072282791138, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7327da152dc243b1970e9abd3983360d6203741604e96941445eb67de94f9a38.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "734d489c1043625027e1a69a6698a3ec677ae146adea5906a7d0121b35b87ace", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7d4fc4eb99cfdeb37a2e5df0ebabd8dda7e0987efc5d0b56b61f2582d593fa79", "generation_seconds_batch": 21.11546836909838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.342509925365448, "target_z": 0.03393552337275789, "ce": 6.141753673553467, "genuineness": 4.557555198669434, "identity": 0.7648096084594727, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/734d489c1043625027e1a69a6698a3ec677ae146adea5906a7d0121b35b87ace.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": "73b5c95eb681cb2129fec06bb051ec61821de725ed70b52cc8badf954132cd68", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6efe45a07021c25d5ece900f180ab3b695e3dcd616ebb31d008f49747097ed56", "generation_seconds_batch": 16.4084937160369, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3385846614837646, "target_z": 3.296874811220857, "ce": 5.80021858215332, "genuineness": 4.074300289154053, "identity": 0.6474701166152954, "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_Fear/73b5c95eb681cb2129fec06bb051ec61821de725ed70b52cc8badf954132cd68.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "741995dd14797f3d786cc6903375295c8c9b2b68f71c2a43fe16f0a76e38952b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6f907b7fb2b9ea34c9577ef21109d62ee0110d7531c04a5fdbfc10db09028312", "generation_seconds_batch": 15.6141521850368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8880888223648071, "target_z": 0.9257812971947857, "ce": 6.260893821716309, "genuineness": 3.9173994064331055, "identity": 0.5048391819000244, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/741995dd14797f3d786cc6903375295c8c9b2b68f71c2a43fe16f0a76e38952b.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "74e45bd3d8167f33e1d483e25841e3d1600648b30527032a8743697403c41401", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f2f1431a699b0fda1ccfd885c8076be3edeed46c38a13fc74760257baf981aa8", "generation_seconds_batch": 23.136461150017567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3827389478683472, "target_z": 1.7343749330138525, "ce": 5.863759994506836, "genuineness": 3.6287014484405518, "identity": 0.20635023713111877, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/74e45bd3d8167f33e1d483e25841e3d1600648b30527032a8743697403c41401.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "756c98acf5225c59f51445f63787fc3b3460a4ba176bce18dd8ed56c081015ce", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6681014cb1258f1853380dd8711d9341353475666b4147927d2efd05ee4a32a4", "generation_seconds_batch": 19.836625437950715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.583466649055481, "target_z": 2.0625000730757974, "ce": 5.895530700683594, "genuineness": 4.055472373962402, "identity": 0.6000503301620483, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/756c98acf5225c59f51445f63787fc3b3460a4ba176bce18dd8ed56c081015ce.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "75f7546e5f768fb0240eb76e960c2fb258027a3f96e6d5f12743213124f84cf2", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "613f0db67cf953323963455ffe41b294d032c502e47a5ffe5983e83e5e7fd59d", "generation_seconds_batch": 20.77032871998381, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4186904430389404, "target_z": 5.062499878207005, "ce": 5.613565921783447, "genuineness": 3.8295347690582275, "identity": 0.5503687858581543, "hypothesis": "J'ai trouvé la 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_Fear/75f7546e5f768fb0240eb76e960c2fb258027a3f96e6d5f12743213124f84cf2.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "7658ab186c98b43fbb5847c53d8b9fb85796e2a7afe0220bec35064762e92b8e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b78330eee99394f6e6bf1049ebaf1b7aa517be82e060568237523ab1e30e43d7", "generation_seconds_batch": 22.118898217915557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.395935535430908, "target_z": 3.3906250182689495, "ce": 5.756534099578857, "genuineness": 3.961331605911255, "identity": 0.4952297806739807, "hypothesis": "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_Fear/7658ab186c98b43fbb5847c53d8b9fb85796e2a7afe0220bec35064762e92b8e.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "766c7af337ca81557c3c659cea22d0fa7fa4779dc2a14e92fb87a39c47d4753f", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b2c06c979db7ef4d17b55e17dab4a15be3983835d744234a89d3e819a4ab3ee7", "generation_seconds_batch": 21.755733020952903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023048341274261475, "target_z": -0.48828127283618666, "ce": 6.078212261199951, "genuineness": 4.494794845581055, "identity": 0.45640063285827637, "hypothesis": "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_Fear/766c7af337ca81557c3c659cea22d0fa7fa4779dc2a14e92fb87a39c47d4753f.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": "77476bc5356b5cd28471db9c93753260b72961fcec395b8a1463b464aa1f2f68", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8c6b070c045ea47cc3ed62d97cadb1b0044f9bde58e66f8262699dc17778f17f", "generation_seconds_batch": 13.719729471951723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21421751379966736, "target_z": -0.17578124847758755, "ce": 6.284721851348877, "genuineness": 4.080576419830322, "identity": 0.5282154083251953, "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_Fear/77476bc5356b5cd28471db9c93753260b72961fcec395b8a1463b464aa1f2f68.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "77636450ff24679d14efa3184a8a8b87f07c62c17d4df2985e033517d0655ca7", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "089242d1d2e245b98855be13d4222fff56854ce02b8ad2190a9480836f9bc968", "generation_seconds_batch": 22.79071933205705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7841942310333252, "target_z": 2.3906250182689495, "ce": 5.77639102935791, "genuineness": 4.15588903427124, "identity": 0.4906589686870575, "hypothesis": "La porte était encore ouverte. J'ai posé tout 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_Fear/77636450ff24679d14efa3184a8a8b87f07c62c17d4df2985e033517d0655ca7.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": "776a50988513fb14feb155fe1c1972aaac89f18d0c1368fa74e570bb719081ac", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0b1046970592e7010c308552ddaa7a2737019de198082f1c9e36ac4bda79d639", "generation_seconds_batch": 14.555862723034807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33250343799591064, "target_z": 0.017578139462918224, "ce": 6.308549880981445, "genuineness": 4.256305694580078, "identity": 0.5693316459655762, "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/776a50988513fb14feb155fe1c1972aaac89f18d0c1368fa74e570bb719081ac.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "778b0a221cd7aae08c9fc28bba16cfe80b10bde599e9b4d8c4842244b7eddd7e", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "79dab9ba786560975bad4bcf8dcc669e0937ed6abaf532285ad0782bdbb8d939", "generation_seconds_batch": 16.259603237966076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008710682392120361, "target_z": -0.5117187271638133, "ce": 6.157639026641846, "genuineness": 4.030367851257324, "identity": 0.38621610403060913, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/778b0a221cd7aae08c9fc28bba16cfe80b10bde599e9b4d8c4842244b7eddd7e.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "249d03ef98872a5ce9e737cf0cb4009f8997c9485801eee7cea91d1f8b596753", "generation_seconds_batch": 16.127161253942177, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.037386029958724976, "target_z": -0.46484376979136177, "ce": 6.022613525390625, "genuineness": 4.406930446624756, "identity": 0.7459548711776733, "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_Fear/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "77e13c686b9994f0d587978704d67536a09a2dff7a068f4b27493c2440c75c6d", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8ba48b7af3ca88391756ad95a74c3d3e89333d1967e7829775e582333ccdaa23", "generation_seconds_batch": 20.197385517065413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7327638864517212, "target_z": 0.671875054806848, "ce": 6.038498878479004, "genuineness": 4.381826400756836, "identity": 0.4745754301548004, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/77e13c686b9994f0d587978704d67536a09a2dff7a068f4b27493c2440c75c6d.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "7807bec8825a0077daf1045526703b116b31ad9356b232fa08c38a6cb2d380c1", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3bb1395d7f5f306cee3f5e467907edfd93102be5cc43668b4939f6b1c0b69de7", "generation_seconds_batch": 26.739957237034105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6276208162307739, "target_z": 0.5, "ce": 6.125868320465088, "genuineness": 3.7667744159698486, "identity": 0.5725851655006409, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7807bec8825a0077daf1045526703b116b31ad9356b232fa08c38a6cb2d380c1.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "7823cefe9fe17690ef17e5227dff29d741d458e21beaf407325459f7c25a9d6a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1a5ff3d13d59979953b05f13dc05dca47fb6faf1a03f7fa8483c1be3283e01fd", "generation_seconds_batch": 16.47285230504349, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2011282444000244, "target_z": 1.4374999269242026, "ce": 5.879645347595215, "genuineness": 4.3881025314331055, "identity": 0.6054091453552246, "hypothesis": "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_Fear/7823cefe9fe17690ef17e5227dff29d741d458e21beaf407325459f7c25a9d6a.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "78652587cb6489dc295e655c458b7a2444b195b9b51c75a52b777d0b5b0331ef", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "229ff4feafa0200186b0f6c5ccf200b3b0e7c50893dfd102bff94ec2ca06e15f", "generation_seconds_batch": 20.126751984935254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3206090927124023, "target_z": 1.6328126309274702, "ce": 5.998785495758057, "genuineness": 4.093128204345703, "identity": 0.6407132148742676, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/78652587cb6489dc295e655c458b7a2444b195b9b51c75a52b777d0b5b0331ef.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "7866a663a7754233c052e11db9190c6a7968a626931e438a189f5d5741b853c8", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2536fb6048da047a05764fefdc90c3404b56f1d614c9d05b63e6db2d7fe6ce32", "generation_seconds_batch": 17.296131321112625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.759049654006958, "target_z": 0.71484381850856, "ce": 6.125868320465088, "genuineness": 3.9550557136535645, "identity": 0.4003683924674988, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7866a663a7754233c052e11db9190c6a7968a626931e438a189f5d5741b853c8.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "78a7a4c251a42f38304be097b4358402594917259869ae856a2ff7e0375d8179", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5a817599daefecaee4c66359e48cb803074779959046fbd9eb249e143ccd3f1f", "generation_seconds_batch": 15.946229357970878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05411332845687866, "target_z": -0.43750002435859914, "ce": 6.1020402908325195, "genuineness": 4.65797233581543, "identity": 0.6435834169387817, "hypothesis": "La porte 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_Fear/78a7a4c251a42f38304be097b4358402594917259869ae856a2ff7e0375d8179.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "78c7221ff044421c6fe4d2324384436083e4a3b9798212ff3e883473f97ed6bf", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8dab359fab99636fbdfb9ff5886aca111cc53edbd7199937910007f1e10fe245", "generation_seconds_batch": 22.254719292046502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10190562903881073, "target_z": -0.3593750060896498, "ce": 5.927301406860352, "genuineness": 4.143336772918701, "identity": 0.5785444974899292, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/78c7221ff044421c6fe4d2324384436083e4a3b9798212ff3e883473f97ed6bf.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "78f2c5d7af2b8a8ab5204b9c52456bf8c3512355febc36eaf5a48dcde4e2b431", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f037804892fe5ab50860d92373c1824e44229449682a81050cc7021570f63a9d", "generation_seconds_batch": 21.790701926103793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9598846435546875, "target_z": 4.3125001705101935, "ce": 5.7406487464904785, "genuineness": 3.6224255561828613, "identity": 0.650679886341095, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Tire aussi en main. Tire aussi une oeil. Tire aussi une poulet porte, Baku. Tire aussi.", "wer": 0.8888888888888888, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/78f2c5d7af2b8a8ab5204b9c52456bf8c3512355febc36eaf5a48dcde4e2b431.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": "7917976a2ca3d9b979dbb46b47ac0c79515323538905af7f7526e64376ff53d0", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ba1f1d967ebd50d58df65915e172c4a66e3077a1e56acd66ffecd454f87c8353", "generation_seconds_batch": 20.602992844069377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.736401915550232, "target_z": 2.312499975641401, "ce": 6.062326908111572, "genuineness": 3.798154592514038, "identity": 0.5495855808258057, "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_Fear/7917976a2ca3d9b979dbb46b47ac0c79515323538905af7f7526e64376ff53d0.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "7939dddc4a4a03bcc37e054c924ac084229605fec31cae5e7a2268bf3c5f60ea", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "43049c9c8da019be68f97d27f13c6cd2b520ff6ded4a2f5871b45ce00eec1a4d", "generation_seconds_batch": 22.294266500044614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03021720051765442, "target_z": -0.4765624969551751, "ce": 6.300607204437256, "genuineness": 4.582659721374512, "identity": 0.5414320826530457, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7939dddc4a4a03bcc37e054c924ac084229605fec31cae5e7a2268bf3c5f60ea.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "96a93681bda84a7261c7ac8314033c2fcff00068e3419cfd44bed9b532b3ba1e", "generation_seconds_batch": 14.289346968987957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06367179751396179, "target_z": -0.4218750060896498, "ce": 6.23706579208374, "genuineness": 4.7081804275512695, "identity": 0.5159188508987427, "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_Fear/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.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": "79767748c31af671966d6fdbf3985a0caec5db557ac8341df7b92d5ad1e65743", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cb32a7fd7ea8a7d9e193bf1567862592f8f8ca3f016b69a993215ee3937378d6", "generation_seconds_batch": 18.734013667912222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2489205598831177, "target_z": 1.5156249695517512, "ce": 5.839932441711426, "genuineness": 4.369274139404297, "identity": 0.5972296595573425, "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_Fear/79767748c31af671966d6fdbf3985a0caec5db557ac8341df7b92d5ad1e65743.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "7a84ff5dd7b169928434dcedf6b98824aac2dcd12b78e32427ae57d00a0bc711", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "011fb98da97360d69cb5d201e2f8fc87c9cf6efccd9247dc1e37241afd9f8c6f", "generation_seconds_batch": 23.03132244409062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18912656605243683, "target_z": -0.21679686662673156, "ce": 6.197352409362793, "genuineness": 4.494794845581055, "identity": 0.5410219430923462, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7a84ff5dd7b169928434dcedf6b98824aac2dcd12b78e32427ae57d00a0bc711.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "7a907b5d9a65c5f6238293b85c51a8863b8608bbbedbad70156a2b63d6cd7467", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "27f90a3da3efc05555e1b5d8bd69904c8dad4d89a75d17d12aedf7e1347699b6", "generation_seconds_batch": 21.03833404404577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019463926553726196, "target_z": -0.49414063641809336, "ce": 6.197352409362793, "genuineness": 4.632867813110352, "identity": 0.6544216871261597, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7a907b5d9a65c5f6238293b85c51a8863b8608bbbedbad70156a2b63d6cd7467.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "7ad5dc54d9a6d25b1c28ad03dd25addb8e583ba657ad79e49674ab7a8adc4484", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e8a87391799295a1f44c2abe2a7bde45f1087f525380696cd2b49d4a2d26ef56", "generation_seconds_batch": 21.414594050031155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07203544676303864, "target_z": -0.40820313337326847, "ce": 6.260893821716309, "genuineness": 4.369274139404297, "identity": 0.6798478960990906, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7ad5dc54d9a6d25b1c28ad03dd25addb8e583ba657ad79e49674ab7a8adc4484.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "7b19838278c2e1b2d340ffc1307b159d5e1511d7a924fc3498dd97b91ac960e7", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a27a359e345fb18ea588f1e5d373ae3ab7502bcdc81a3604b85ee450f8f03d1d", "generation_seconds_batch": 21.76435483293608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0338016152381897, "target_z": -0.47070313337326847, "ce": 6.181467056274414, "genuineness": 4.582659721374512, "identity": 0.7044079303741455, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7b19838278c2e1b2d340ffc1307b159d5e1511d7a924fc3498dd97b91ac960e7.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "7b26367726c0a9aa7e0b598c3752f06ede70071469cdfa1eede6267f4e846538", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a0eef8b149ff73402af7d7382b9056889b8ecf7df329502abec64c762ee8b304", "generation_seconds_batch": 22.74565862293821, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4150524139404297, "target_z": 3.4218749573724514, "ce": 5.808161735534668, "genuineness": 3.8169827461242676, "identity": 0.14879806339740753, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7b26367726c0a9aa7e0b598c3752f06ede70071469cdfa1eede6267f4e846538.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "7b2d00ada11f22ba4230c9bc27e68b1d7c45e0267692948275ab3ad784655ad0", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a7c90633aea503aadab989b278b12700d38149a0beee0a448c5b15eaf5620c54", "generation_seconds_batch": 15.57541972398758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6098597049713135, "target_z": 5.375000048717198, "ce": 5.911416053771973, "genuineness": 3.4435582160949707, "identity": 0.8109899759292603, "hypothesis": "The door is still open. Put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7b2d00ada11f22ba4230c9bc27e68b1d7c45e0267692948275ab3ad784655ad0.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "7c865a81779592faf42fc969daf215525a0c4b6586924b4e60f6a1b8fc2c5c8c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4a996a1e313fefdf527af97a7ddd1d60002ea17eaa80c3cdf57e671ed595116e", "generation_seconds_batch": 22.669859299901873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09712640941143036, "target_z": -0.3671874908655253, "ce": 6.006728172302246, "genuineness": 4.532451152801514, "identity": 0.6981357336044312, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7c865a81779592faf42fc969daf215525a0c4b6586924b4e60f6a1b8fc2c5c8c.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "7cc313eb84fda5a28853627982dbb9204290f7a6a013832c08bdc0c8c3bd6779", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1b40b12cc0a21e8fe43d704539ff0b7b294fa424ed9cbd361304e2bb90361f4a", "generation_seconds_batch": 15.684888810967095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10429525375366211, "target_z": -0.3554687393431129, "ce": 6.109982967376709, "genuineness": 4.281409740447998, "identity": 0.7188569903373718, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7cc313eb84fda5a28853627982dbb9204290f7a6a013832c08bdc0c8c3bd6779.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "7cd944390b4ba15c98ffde583b3aeeb641c9320823b8aa38fd8a45bd2787538d", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "61a8b848b791be049a7f788db44bb6c7749385cb64ea49fab5ff5f061f9882cc", "generation_seconds_batch": 15.103446474997327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08995756506919861, "target_z": -0.3789062423879378, "ce": 5.863759994506836, "genuineness": 4.482243061065674, "identity": 0.6746214628219604, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7cd944390b4ba15c98ffde583b3aeeb641c9320823b8aa38fd8a45bd2787538d.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "7d0decfc2ed7c8d09e40f73cb8a1481c46e866cac1d8bd1a4975cc2c257772c1", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8c1ffd3b706e4c48bb167b0c60f00d5b4113fc5b7339d9443ea53f3aec126118", "generation_seconds_batch": 15.726269257022068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08637313544750214, "target_z": -0.3847656303284436, "ce": 6.1020402908325195, "genuineness": 4.3504462242126465, "identity": 0.46765872836112976, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7d0decfc2ed7c8d09e40f73cb8a1481c46e866cac1d8bd1a4975cc2c257772c1.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "7d18aa9d69b7d1132e03ed0708805146767be7ad5ea569f14dc19746aef5789a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "703a6cbdaa9d385e65292225ee740917f86b3f5b5dbdbfe3d2526f8de8bba2ac", "generation_seconds_batch": 16.214119294076227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04336008429527283, "target_z": -0.4550781151043191, "ce": 6.062326908111572, "genuineness": 4.632867813110352, "identity": 0.46311405301094055, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist. Schettestes genieße ich dicht.", "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_Fear/7d18aa9d69b7d1132e03ed0708805146767be7ad5ea569f14dc19746aef5789a.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "7d3913e0f763b45b51ff387a07b74cc1176386a60fd74726a36a800cd3cb3fe3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "cc7dc11a4132c56a8decd322bb1a46cd33eec3af654405d151425166b43e3b10", "generation_seconds_batch": 15.276812607073225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.481961727142334, "target_z": 3.531250133972295, "ce": 5.784333229064941, "genuineness": 4.105680465698242, "identity": 0.6967980861663818, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7d3913e0f763b45b51ff387a07b74cc1176386a60fd74726a36a800cd3cb3fe3.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "7dac373234917f801565447a8633785fc53c1448e901f9508b18f52b126d0d63", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "fa34b270b39cc79e84e1b7d002e369214c9ba826e759866d39b2f988fc866ed0", "generation_seconds_batch": 22.214332742034458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12341216206550598, "target_z": -0.3242187515224124, "ce": 6.038498878479004, "genuineness": 4.268857479095459, "identity": 0.6032010316848755, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7dac373234917f801565447a8633785fc53c1448e901f9508b18f52b126d0d63.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "7dccf620cd264836b2c8eb63ecb9f45a43808f3c19ceb962a6f0aa95c64e6fe6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4d67534080bfa35aca3ebe4b2d406eb105575bc55dd3decc55f78a38f5b8fba1", "generation_seconds_batch": 22.218551547033712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09951601922512054, "target_z": -0.3632812484775876, "ce": 5.863759994506836, "genuineness": 4.381826400756836, "identity": 0.39318370819091797, "hypothesis": "La puerta sigue apierta. 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_Fear/7dccf620cd264836b2c8eb63ecb9f45a43808f3c19ceb962a6f0aa95c64e6fe6.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "7e22ab50ef3581a6fd1744c34a04f172e0740feeba020779a87a10c810a1829c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "67a0c10702df1f603cc3e2ec1e738cc065fa4c9158b217eca0b123e68131f150", "generation_seconds_batch": 22.88805532094557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3827389478683472, "target_z": 1.7343749330138525, "ce": 5.178704738616943, "genuineness": 3.8420867919921875, "identity": 0.37252503633499146, "hypothesis": "De daar staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7e22ab50ef3581a6fd1744c34a04f172e0740feeba020779a87a10c810a1829c.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "7e23a7cf6b3eea4ef46538bba0a3c69ff16ed2d94d318ba313c913388a477295", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "227839aa549493d786055c7d8d85b471c212cd8de6930463360587c3003fe728", "generation_seconds_batch": 20.41035237594042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5871047973632812, "target_z": 3.703125188779143, "ce": 5.736677646636963, "genuineness": 3.9676074981689453, "identity": 0.6349853873252869, "hypothesis": "J'ai trouvé la 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_Fear/7e23a7cf6b3eea4ef46538bba0a3c69ff16ed2d94d318ba313c913388a477295.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": "7e42669b01de7592a1667e8eb276f7ec18b4075eec57171c5a2f4376a498be26", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0aff69f3a4ec10f2dc2bfec82c906ad02bb5be287e07d38b9885db8527e3ee60", "generation_seconds_batch": 15.401366346981376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26051628589630127, "target_z": -0.100097668238998, "ce": 6.054384231567383, "genuineness": 4.293961524963379, "identity": 0.45604175329208374, "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_Fear/7e42669b01de7592a1667e8eb276f7ec18b4075eec57171c5a2f4376a498be26.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "7ebff28ca761314991c3dd601433997b72630c2589809786f60ab7798b54e48c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "512f11ef3a387e7af327e3aa493e36b6ba3a8afead0c784da74d82e23630c53f", "generation_seconds_batch": 22.397855408024043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0481929779052734, "target_z": 1.1875000243585991, "ce": 5.911416053771973, "genuineness": 4.011539936065674, "identity": 0.4581223428249359, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7ebff28ca761314991c3dd601433997b72630c2589809786f60ab7798b54e48c.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "318cd809f90117be892adce63e3295658e650e86f2d2bacb7f619e4ad0ab9d45", "generation_seconds_batch": 17.07335184898693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003237396478652954, "target_z": -0.5312499878207004, "ce": 6.38797664642334, "genuineness": 4.419482707977295, "identity": 0.3282812535762787, "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_Fear/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.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": "7f717eefdcf83a41a55b72c8224b2839728653bf99895c5b5d622b97e44fdedb", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "342dbab2266d8420e847bae202521cb9b7b135c4b00118d08d98f42feb6ec246", "generation_seconds_batch": 22.416082616895437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5739080905914307, "target_z": 2.046874908655253, "ce": 5.657250881195068, "genuineness": 4.086852550506592, "identity": 0.5676686763763428, "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_Fear/7f717eefdcf83a41a55b72c8224b2839728653bf99895c5b5d622b97e44fdedb.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "7fcb6d253d9db9f552198d8062a10dfb82768cc1173632b80c4e0cf09cdbe7aa", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "57f82e48777498f7777af072c285ac96c230ee8c530e767fa9fdc76ae32f94ba", "generation_seconds_batch": 23.002459125011228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47826990485191345, "target_z": 0.25585936358190664, "ce": 6.109982967376709, "genuineness": 4.632867813110352, "identity": 0.79307621717453, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7fcb6d253d9db9f552198d8062a10dfb82768cc1173632b80c4e0cf09cdbe7aa.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "7fe7bd79875e51bdda9fadfdbce9e4c76511fab65f96532651c629f56d93a9ca", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "02668476e0435c17e73a3cde032c17fc3575cd9ec1f3ef3d5b80fd969914d96f", "generation_seconds_batch": 16.09815986698959, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9311018586158752, "target_z": 0.9960937576120622, "ce": 5.577824115753174, "genuineness": 4.21237325668335, "identity": 0.5595043301582336, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/7fe7bd79875e51bdda9fadfdbce9e4c76511fab65f96532651c629f56d93a9ca.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "8038ad8524e08a0ac69b3376de11f38c3668c81f48f5f107cc52dbbefa1f4ad6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d94de5e15ee367297a92d1c722c03ab9f73a254643796bb9447092d415b9c12c", "generation_seconds_batch": 15.515750481979921, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00562700629234314, "target_z": -0.5351562302086382, "ce": 6.316492557525635, "genuineness": 4.507347106933594, "identity": 0.6653784513473511, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8038ad8524e08a0ac69b3376de11f38c3668c81f48f5f107cc52dbbefa1f4ad6.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "80449d4e2b40082fe0b2d703d8528767025168e7681f5748d198a65795773b46", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "75ea06916492e10f1325aee6c55f456d471a3acfb54f512911afef12b864b9a6", "generation_seconds_batch": 25.35776079900097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015879511833190918, "target_z": -0.5, "ce": 6.181467056274414, "genuineness": 4.419482707977295, "identity": 0.583147406578064, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/80449d4e2b40082fe0b2d703d8528767025168e7681f5748d198a65795773b46.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "804fecd6ba782abc98a3a06e7a9dace793ef55703bf9b862a135087eb0863420", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "00c843025b4996979120ee9d158d8b7dfced73f951eca6d499bdbb0819ef62cb", "generation_seconds_batch": 20.857606638921425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.787832260131836, "target_z": 4.031249939103502, "ce": 6.173524379730225, "genuineness": 3.672633647918701, "identity": 0.5854424238204956, "hypothesis": "The 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_Fear/804fecd6ba782abc98a3a06e7a9dace793ef55703bf9b862a135087eb0863420.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "8054ad3c24bf33cf760bf2312c837235e6afce48d3a918a96ad544b3de23a783", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4534848b3411486759224aebdeb76a8340d6093851e65a0ff9c7fa0aaea594d6", "generation_seconds_batch": 21.651122921030037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03977566957473755, "target_z": -0.46093747868622575, "ce": 5.982900142669678, "genuineness": 4.494794845581055, "identity": 0.6373555064201355, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8054ad3c24bf33cf760bf2312c837235e6afce48d3a918a96ad544b3de23a783.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "29e6d2e980832d23181980476fd603675dbf11a63f456cabd8d8f89bbf90264d", "generation_seconds_batch": 13.421577680972405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.042165279388427734, "target_z": -0.457031236298288, "ce": 6.117925643920898, "genuineness": 4.469690799713135, "identity": 0.7708878517150879, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "80c61216ba02a78e09166f50075448b9976add6c20a31d5c2f300d2371144de9", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0935d2ee866ba86f5db53ec155b1ad936429a967b736dbae0df30ec0992464fd", "generation_seconds_batch": 15.665517495013773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3481433391571045, "target_z": 3.312500170510194, "ce": 5.5659098625183105, "genuineness": 4.193545341491699, "identity": 0.7668712139129639, "hypothesis": "J'ai trouvé la petite boîte. Elle était prête. Elle était prête la vue fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.2631578947368421, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/80c61216ba02a78e09166f50075448b9976add6c20a31d5c2f300d2371144de9.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "8138f0c0a2a6d11c05ad18f8dff930c11bc008227bbc2bd5d3e19953134de98d", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "deb3bed05a0047353f65e1144212a294ae92cb2b5c89e6918f164a39a07c8fb7", "generation_seconds_batch": 24.20421591901686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.548870801925659, "target_z": 3.640624920834553, "ce": 5.990842819213867, "genuineness": 3.5565271377563477, "identity": 0.47528424859046936, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude graam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8138f0c0a2a6d11c05ad18f8dff930c11bc008227bbc2bd5d3e19953134de98d.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "8156099af37c32ac7c3cb52253cb1d1b10b1768127d7620102e11cd362910780", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6c919db2b71fe6f06f81636ca82538769b1cb02de0e59dc89918f260e07d617c", "generation_seconds_batch": 17.849984709988348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2345829010009766, "target_z": 1.4921875152241244, "ce": 6.070269584655762, "genuineness": 4.017816066741943, "identity": 0.5212565660476685, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8156099af37c32ac7c3cb52253cb1d1b10b1768127d7620102e11cd362910780.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": "8157d063fa9dbdfd43955325a5cc3b821d5265369a947599339cce0252d63160", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1139be25cd0b17174495357b74570d188baeec1bd2caa3267aaa92ccc6903a18", "generation_seconds_batch": 21.06732575793285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.826066017150879, "target_z": 4.093749817310506, "ce": 5.95112943649292, "genuineness": 3.7793264389038086, "identity": 0.5008195638656616, "hypothesis": "Alguien movió la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "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_Fear/8157d063fa9dbdfd43955325a5cc3b821d5265369a947599339cce0252d63160.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "81736dae5b35a892b612da97fce5489223a7a855f84021c2624f753d06d02d90", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "59dc6f059ec13d07c707ea8099723450372d708c7411322cc89eecbe30821270", "generation_seconds_batch": 21.70229421998374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8450757265090942, "target_z": 0.8554687393431128, "ce": 5.824047088623047, "genuineness": 4.068024158477783, "identity": 0.30097702145576477, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/81736dae5b35a892b612da97fce5489223a7a855f84021c2624f753d06d02d90.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "81cd756e54fc3479f797982c269edd93d31ae4e110601708bd49b10dcb552c9d", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "348ae0135efd8be04e2e591f5e251cf86f52e702a84d3d510cbd69af65792ecc", "generation_seconds_batch": 22.88805532094557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4018559455871582, "target_z": 1.7656250669861475, "ce": 5.645336627960205, "genuineness": 3.562803030014038, "identity": 0.5024162530899048, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/81cd756e54fc3479f797982c269edd93d31ae4e110601708bd49b10dcb552c9d.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "81dada14a197169e9dabbec5be7ac5747e24658df7e0bb54771550a7da8abb7f", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "673b4e01c2f5e780d35ceefe300be8a4cdbd5b5318294fab29da306480492837", "generation_seconds_batch": 20.623070504982024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2334418296813965, "target_z": 3.125000146151595, "ce": 5.621508598327637, "genuineness": 4.068024158477783, "identity": 0.7294868230819702, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/81dada14a197169e9dabbec5be7ac5747e24658df7e0bb54771550a7da8abb7f.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "8210067d059e4fe293cb4c99b2c6ff298129bf72586767a61357b1b45d3ebcee", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "118caf6943f5194f9bb1e2a343f5c92d21356b668194fb2723303982cbda7f1d", "generation_seconds_batch": 21.619219220010564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.701698899269104, "target_z": 0.6210938063292605, "ce": 6.086154937744141, "genuineness": 4.319066047668457, "identity": 0.5905191898345947, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8210067d059e4fe293cb4c99b2c6ff298129bf72586767a61357b1b45d3ebcee.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "8255444739438310abfc34fd07eb89706999740fc479e42f40f8b3983f626c12", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "aa6157c14f71c1b6f879fd3c2528aff4d19e553791082d318ac113d0a76167cd", "generation_seconds_batch": 15.199476376990788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.908454179763794, "target_z": 2.5937500121792993, "ce": 6.022613525390625, "genuineness": 4.231201171875, "identity": 0.6482217907905579, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8255444739438310abfc34fd07eb89706999740fc479e42f40f8b3983f626c12.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": "82c00f9d6ba1eb657fa7a6cfca167105970816305a91e45f4c0182de90b8470e", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2d84e952e651dd1cd8af187e9032224445a86fa079dc3a0f7d73f9a0eedba1ec", "generation_seconds_batch": 16.520975314080715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9526084065437317, "target_z": 1.0312500365378987, "ce": 6.054384231567383, "genuineness": 3.823258876800537, "identity": 0.289624959230423, "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_Fear/82c00f9d6ba1eb657fa7a6cfca167105970816305a91e45f4c0182de90b8470e.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "832cbf23d566477d4e28d68631f19d59c78266588fbe08a7f46d66f265afc216", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "77e414e904def0a3122907f61f60795e0ddaff4dcabab70adb0b353773be2daa", "generation_seconds_batch": 15.593859028071165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3118930160999298, "target_z": -0.01611326202954289, "ce": 6.181467056274414, "genuineness": 4.632867813110352, "identity": 0.7118287086486816, "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_Fear/832cbf23d566477d4e28d68631f19d59c78266588fbe08a7f46d66f265afc216.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "836b09253737b11a940e8cceceb692de6bead0196747dca7c30ae2ad2583e65e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f098c20dc36b5ca6117c75d3847b9d1f9881d17121a1ab0fb86510aa52d71c7c", "generation_seconds_batch": 20.523497524904087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.061282187700271606, "target_z": -0.4257812484775876, "ce": 6.348263263702393, "genuineness": 4.2249250411987305, "identity": 0.4912128448486328, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/836b09253737b11a940e8cceceb692de6bead0196747dca7c30ae2ad2583e65e.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": "83a72e2b70a112d9ea94c41795355eb96214ccaf66678013b6ea03f12d6524ff", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9cead289afad02debb20a2e8bab680fd532f0a379eb79f859bf9245dd3bb395b", "generation_seconds_batch": 15.916303651058115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7591569423675537, "target_z": 3.984375030448249, "ce": 5.804190158843994, "genuineness": 3.9299514293670654, "identity": 0.7235509753227234, "hypothesis": "La route tourne à gauche après le pont. Continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/83a72e2b70a112d9ea94c41795355eb96214ccaf66678013b6ea03f12d6524ff.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "83f76a2707222b405185d173a2c98950d1477abce7d444d2551ac938b82b5c7f", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "57753b86295f60dd5ec4211de4fece15284d2408edbd6a52b249918e194a2f65", "generation_seconds_batch": 20.608600694919005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8128695487976074, "target_z": 2.4374999269242026, "ce": 5.732706069946289, "genuineness": 4.068024158477783, "identity": 0.641403317451477, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/83f76a2707222b405185d173a2c98950d1477abce7d444d2551ac938b82b5c7f.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "83fe388ee2b787afd5a648b3a20640a59d2431c550461bba0e05768032e2a9f3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7daffd66172e838413185b010df1a48e497bf9bf5409f528fa6c28a299c681ec", "generation_seconds_batch": 20.623070504982024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.979001522064209, "target_z": 4.343750109613696, "ce": 5.327630043029785, "genuineness": 3.936227321624756, "identity": 0.6408785581588745, "hypothesis": "J'ai trouvé la 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_Fear/83fe388ee2b787afd5a648b3a20640a59d2431c550461bba0e05768032e2a9f3.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "84329bf336810af98e38015e0cf500ae354f48745695fc00737018ad739c8ec2", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7058fea9aa42a72aafbaca5cba8890575313e5f54652b76e021fe82c2054dede", "generation_seconds_batch": 16.7651406689547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8451831340789795, "target_z": 4.125000146151595, "ce": 5.792276382446289, "genuineness": 3.9048471450805664, "identity": 0.3936976194381714, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Díame 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_Fear/84329bf336810af98e38015e0cf500ae354f48745695fc00737018ad739c8ec2.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": "8435db0b584bf1db191e6c89e8578a8d4854c108068dd8235b148d3578846eec", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c73cc7b32058d32d2711f687da88a67d23e5313638abdff7d08a7fe697f016bc", "generation_seconds_batch": 15.525528879021294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3577017784118652, "target_z": 3.3281251400619447, "ce": 5.839932441711426, "genuineness": 3.773050308227539, "identity": 0.7186589241027832, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le détener, après le déjeuner.", "wer": 0.14285714285714285, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8435db0b584bf1db191e6c89e8578a8d4854c108068dd8235b148d3578846eec.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "845d9af05d11445e40ec5a7666ef4fb64589daf456c6f60983e4df34a3650c2b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e68f96f90d8ecbc609b12a46df90aea963e8c408ec5f16e0e12d0e06d8d20202", "generation_seconds_batch": 21.79202737205196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0745859146118164, "target_z": 4.499999805131207, "ce": 5.375286102294922, "genuineness": 3.8169827461242676, "identity": 0.5985095500946045, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. Vija, podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/845d9af05d11445e40ec5a7666ef4fb64589daf456c6f60983e4df34a3650c2b.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "853414f7984ab45f7439fa756599bee409389119a6e121c406c700aff6ab5e8e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "908a8cfd6a6985e0916817a28176cca6aebc45fe3b4d9bc7806c6431690e2b39", "generation_seconds_batch": 20.56469000002835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2082434743642807, "target_z": -0.1855468788060311, "ce": 5.764476776123047, "genuineness": 4.287685871124268, "identity": 0.05702453479170799, "hypothesis": "De deur staat nog open. Ik heb je jas op de op de stoel gelegd. Zeg maar 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_Fear/853414f7984ab45f7439fa756599bee409389119a6e121c406c700aff6ab5e8e.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "85c267d693a93b80ba68fa7b34bf22d12b0f654fe56fe654353e777553f19cbd", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4aefad74d0bd63d23336887702963ef56cf252a62877a92c00a89b0e41574c1e", "generation_seconds_batch": 22.962561806081794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.405493974685669, "target_z": 3.4062499878207007, "ce": 5.40705680847168, "genuineness": 4.168440818786621, "identity": 0.6011211276054382, "hypothesis": "La porte 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_Fear/85c267d693a93b80ba68fa7b34bf22d12b0f654fe56fe654353e777553f19cbd.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "86603413c9c1da7111ea9e582d668a2fdb85ddfb1daaffa057caf8bc2ee3ed15", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "08dd7900739254d5b3c5fbf2bc90f6d443af6121b7c10500ee6003d31387e4fe", "generation_seconds_batch": 14.164195736986585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0911523699760437, "target_z": -0.3769531211939689, "ce": 6.078212261199951, "genuineness": 4.494794845581055, "identity": 0.7108156681060791, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/86603413c9c1da7111ea9e582d668a2fdb85ddfb1daaffa057caf8bc2ee3ed15.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "8680816abd962a86c078d5b0efc51e359557ba391f097c3409eae7fb3575b695", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4a503a9a0234bd50209037bf081073756f369971092f50177339014e9b79849b", "generation_seconds_batch": 14.52274145197589, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10907447338104248, "target_z": -0.3476562545672373, "ce": 5.95112943649292, "genuineness": 4.105680465698242, "identity": 0.45135095715522766, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8680816abd962a86c078d5b0efc51e359557ba391f097c3409eae7fb3575b695.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "869583884b824a8cec15f953d46e9d1a53c12f4d126f0b9af53316b18a4bd137", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2c9ca9a268165eaf6ba0ad7f0a584a0d02371f0259904b6e039c9c940d4f5770", "generation_seconds_batch": 21.11546836909838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21003568172454834, "target_z": -0.18261719701507778, "ce": 5.77639102935791, "genuineness": 4.419482707977295, "identity": 0.7695691585540771, "hypothesis": "J'ai trouvé la 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_Fear/869583884b824a8cec15f953d46e9d1a53c12f4d126f0b9af53316b18a4bd137.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "86ccfa231d76ed3b0ffd1eed69369912cfe848a7e5c08ec216c363a051765296", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "7f5b659ad429d6f37ff9d18e8db90bf6147e0b9ddf9a782445f91eb2e19eaa94", "generation_seconds_batch": 22.14964445598889, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5750492811203003, "target_z": 0.414062472596576, "ce": 5.510311126708984, "genuineness": 4.3127899169921875, "identity": 0.8382152915000916, "hypothesis": "J'ai trouvé la 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_Fear/86ccfa231d76ed3b0ffd1eed69369912cfe848a7e5c08ec216c363a051765296.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "87523b8f73f9225f7c2d02cc75595c87e7ce40631877c5b0fd7458f3736a90af", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5945ee9267a9b46e3d831683bee047c229cf29f2d6f9cf3cfe42e72cc0079b01", "generation_seconds_batch": 19.903555126977153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5452327728271484, "target_z": 2.0, "ce": 5.879645347595215, "genuineness": 4.243753433227539, "identity": 0.5977908372879028, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/87523b8f73f9225f7c2d02cc75595c87e7ce40631877c5b0fd7458f3736a90af.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "87c4adf6b2a71a1ff96bc9b166e62bf548738745b603b4e71df7d4b075892a08", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4707f341fc85448c4b20eb3e8d2e670b6a272f206ad521c66df60d18bf6ea80c", "generation_seconds_batch": 21.280625435058028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.56434965133667, "target_z": 2.0312499391035024, "ce": 5.391171455383301, "genuineness": 3.565941095352173, "identity": 0.006639253348112106, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/87c4adf6b2a71a1ff96bc9b166e62bf548738745b603b4e71df7d4b075892a08.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "880ec809bd4312afc7e23673dce31f6c141b8ede49e3acfe6af0b291c9bdd11a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d159f172fa651042274bb5944e67f16ab0b1b7475f8f1614ab67e7f72b535971", "generation_seconds_batch": 19.83656606695149, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.481961727142334, "target_z": 3.531250133972295, "ce": 5.657250881195068, "genuineness": 3.6977379322052, "identity": 0.6499624252319336, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/880ec809bd4312afc7e23673dce31f6c141b8ede49e3acfe6af0b291c9bdd11a.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "892068dee3a5d8d7227b64faa6048f57d21e8588fdae7ed3198869bf5acec01d", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9e6c8e6b066a30400be1cc5a31db2c5e64656a2d196a4a3e79f98d116c47b370", "generation_seconds_batch": 21.738011996028945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4353104829788208, "target_z": 1.8203124604172765, "ce": 5.895530700683594, "genuineness": 4.093128204345703, "identity": 0.7111269235610962, "hypothesis": "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_Fear/892068dee3a5d8d7227b64faa6048f57d21e8588fdae7ed3198869bf5acec01d.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": "892fa3d261dedfd659326a24c04a28854b68b06024ac452f92b933611514c2df", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "230fd4c3090458d03d6abc901804035f2d3639bb3c4ae6ccbe8ce3bf1dba84c5", "generation_seconds_batch": 21.121772763086483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9981184005737305, "target_z": 4.375000048717198, "ce": 5.935244083404541, "genuineness": 3.8922953605651855, "identity": 0.6476520299911499, "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. Noch.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/892fa3d261dedfd659326a24c04a28854b68b06024ac452f92b933611514c2df.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "893533f37d8df424075329d68fa5b97d31178758712e67f555161994ed39e56f", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "218059e065f2caba10fa54c9c751e668dae501b2a83e7444a12d0e6c679a1aff", "generation_seconds_batch": 20.542312616016716, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04455488920211792, "target_z": -0.4531249939103502, "ce": 6.157639026641846, "genuineness": 4.042920112609863, "identity": 0.5100666284561157, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/893533f37d8df424075329d68fa5b97d31178758712e67f555161994ed39e56f.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "89603fb7e7f785cb304b274f645a35abe0eee00dca9ea315b0be1aaa63b10223", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "40e14066fcfb3ffdf8037a5fef0899d419ba7f93892a350d0cf817ad9b35bb40", "generation_seconds_batch": 21.93709330202546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29561376571655273, "target_z": -0.042724593104217, "ce": 6.046441555023193, "genuineness": 4.645420074462891, "identity": 0.7030572891235352, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/89603fb7e7f785cb304b274f645a35abe0eee00dca9ea315b0be1aaa63b10223.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "89873265cc721218200cc13926b2362ee1ffa2103eb1ab6ab985c0f6ae0a6185", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "89429f09ad51de5476704ed606f299ebb21bb97d181ea7f5b41db2c8baf52e18", "generation_seconds_batch": 15.970283002010547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39015287160873413, "target_z": 0.11181639540281134, "ce": 6.046441555023193, "genuineness": 4.256305694580078, "identity": 0.5397489070892334, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo. Ah.", "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_Fear/89873265cc721218200cc13926b2362ee1ffa2103eb1ab6ab985c0f6ae0a6185.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "89b4ba74f5a2b04fc5fc7a2c12a66b4289036be04b9e2bc67fd6863bab40dcb6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "66a786b65b9336d62fbe159f3fd9e109290fd16f5cc91cd040ce926f6ac66839", "generation_seconds_batch": 15.665517495013773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6922476291656494, "target_z": 3.874999853848405, "ce": 5.550024509429932, "genuineness": 3.9550557136535645, "identity": 0.6592200994491577, "hypothesis": "J'ai j'ai trouvé la petite boîte, elle était prête de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/89b4ba74f5a2b04fc5fc7a2c12a66b4289036be04b9e2bc67fd6863bab40dcb6.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "89c0c67056b02f1e7cfb31a6403abddc72f64c0005da9bc495b192996a50d671", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "edc59965a9b94832bfadbfff0a9a838f1a0487404fb7a31f263035ccafa0ea91", "generation_seconds_batch": 20.385860246024095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.85110342502594, "target_z": 2.5, "ce": 5.25614595413208, "genuineness": 3.625563621520996, "identity": 0.4475277066230774, "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_Fear/89c0c67056b02f1e7cfb31a6403abddc72f64c0005da9bc495b192996a50d671.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "8a06be9f2cae759409ee588c047a28aa3f273b2e02385f8fea9064f6467f3642", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "32a2b0b5459eb777174bffb457d38c2fc96be3558cfb8d762812333919b21269", "generation_seconds_batch": 20.593806007993408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 4.049548625946045, "target_z": 6.093749817310506, "ce": 5.855817794799805, "genuineness": 3.452972412109375, "identity": 0.6829585433006287, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8a06be9f2cae759409ee588c047a28aa3f273b2e02385f8fea9064f6467f3642.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "8a4e434e113492facb6342e06140b086ed59e713d65e5c7677140efc5baf0ab4", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d551130d837e452029debc8f200213092857a4cac1c886d9b29831dbac971304", "generation_seconds_batch": 21.259963909047656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1091818809509277, "target_z": 2.9218751522412445, "ce": 5.696964263916016, "genuineness": 3.8295347690582275, "identity": 0.6985894441604614, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8a4e434e113492facb6342e06140b086ed59e713d65e5c7677140efc5baf0ab4.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "8a59387a6411bb6dccf2824e2bd7cb1c31e6a430d412b86ed989f5c06300aa04", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "33c57b4a21e62b4d66bea79dea419d6fc4ab654b5b60357b78f4da5efe2c05ec", "generation_seconds_batch": 21.160569493076764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4150524139404297, "target_z": 3.4218749573724514, "ce": 5.6254801750183105, "genuineness": 3.6663577556610107, "identity": 0.638176679611206, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.4666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8a59387a6411bb6dccf2824e2bd7cb1c31e6a430d412b86ed989f5c06300aa04.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "8b4006f33ba5b9d7859ebba3157be27bbec72eb0a4c9fc4353e128d082f695f3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "133b44ce34772a78994fff8104eed287b412cb5f53031df565b1bd220ff8df74", "generation_seconds_batch": 21.810549877933227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.55250883102417, "target_z": 5.281249841669106, "ce": 5.355429172515869, "genuineness": 3.5314228534698486, "identity": 0.5741512775421143, "hypothesis": "J'ai trouvé la petite boîte. Elle était prête. Elle était prête. La vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.21052631578947367, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8b4006f33ba5b9d7859ebba3157be27bbec72eb0a4c9fc4353e128d082f695f3.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "8b619849f236922041ad267b1077045a916b3896c0b0f8c178fd0fdf51c4f86b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2258a423b263ed40d52bdd2660da2e248392f7598ed1a0c2faa4641bb52962ac", "generation_seconds_batch": 15.189673496992327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.170170545578003, "target_z": 4.656249890386304, "ce": 5.879645347595215, "genuineness": 3.9173994064331055, "identity": 0.5130027532577515, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8b619849f236922041ad267b1077045a916b3896c0b0f8c178fd0fdf51c4f86b.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "8bd2f0191929b30815d67703937ec1537099c8d776cbca19aab0a93dc3235eea", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d13893a6d4c8e95ad0145d9bc9b72b1029ecf49ea457d58f7da816f49740c2cc", "generation_seconds_batch": 21.023496010922827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1510536670684814, "target_z": 4.624999951282802, "ce": 5.470598220825195, "genuineness": 3.6977379322052, "identity": 0.5550763607025146, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8bd2f0191929b30815d67703937ec1537099c8d776cbca19aab0a93dc3235eea.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "8c512d0c8d8ace8dcc9b9c4e15dc50e90c9e77e07c2940373d13d27f25553945", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9ff1a0d6aac6c9d62e6d20ff7bcbc82b26ba35307226f5f64cd08b1e3cac7e0d", "generation_seconds_batch": 22.74565862293821, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7172850370407104, "target_z": 2.2812500365378985, "ce": 5.847874641418457, "genuineness": 4.168440818786621, "identity": 0.22460488975048065, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8c512d0c8d8ace8dcc9b9c4e15dc50e90c9e77e07c2940373d13d27f25553945.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "8caca8beb27b52240737f56edeee4e8cd28d0ca9ab5dcc2f65972fd7a69f07bd", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "433a19a82ae1119ccc5d95c576f0f177f34b8fe0d58969fe9efbc0626231d493", "generation_seconds_batch": 27.507756265928037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10429525375366211, "target_z": -0.3554687393431129, "ce": 5.673136234283447, "genuineness": 4.293961524963379, "identity": 0.6142750978469849, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8caca8beb27b52240737f56edeee4e8cd28d0ca9ab5dcc2f65972fd7a69f07bd.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "8d1137653945c918fcf2cba047017bb712cc12bd387c97504476095ebb6e8730", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "37babca210c429c9700c349a85bb5f47da4c56c44c15fdded987e27b8799bbf6", "generation_seconds_batch": 15.355206076055765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11385370790958405, "target_z": -0.3398437454327627, "ce": 5.879645347595215, "genuineness": 4.582659721374512, "identity": 0.6695595383644104, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8d1137653945c918fcf2cba047017bb712cc12bd387c97504476095ebb6e8730.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "8d2f358f95eb054ad9ca6d88351570af1c3ebff635916afccbc7ecfc931ce028", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4ee936315a184fe98bdbaa833678cc2aba77e49a18587ba946c935923a0b693c", "generation_seconds_batch": 20.00157908804249, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03499642014503479, "target_z": -0.46875001217929957, "ce": 6.046441555023193, "genuineness": 4.3881025314331055, "identity": 0.5837196111679077, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8d2f358f95eb054ad9ca6d88351570af1c3ebff635916afccbc7ecfc931ce028.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "8dec0fd6755d3e68f26471864b5b75f3a2af9ca8ede7fa70c3bb1714de6a8690", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "474a3cbe387189848db0357c01286c83106891d68fa35b762e70bb1a1c2fdaa8", "generation_seconds_batch": 20.593806007993408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.864300012588501, "target_z": 4.156250085255097, "ce": 5.657250881195068, "genuineness": 3.6224255561828613, "identity": 0.46386459469795227, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8dec0fd6755d3e68f26471864b5b75f3a2af9ca8ede7fa70c3bb1714de6a8690.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "8e0ed8f521d3390e96cff3a9ddcee70c49c85500a7d68f680025e246eb32d534", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c5a04c3f87f7ae8f59073b9c942e172163866d8222246f09a118c7c9acbdae9b", "generation_seconds_batch": 21.73516182496678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.246638298034668, "target_z": 4.781250036537899, "ce": 5.728734970092773, "genuineness": 4.005263805389404, "identity": 0.5544682741165161, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8e0ed8f521d3390e96cff3a9ddcee70c49c85500a7d68f680025e246eb32d534.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "8eda5c7024a38127d14bf19da82c8b9aab818f9763e7f85d9fae4485b9f87573", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ad462c67499aa7bbfdc8dbe0489f79b248d5059242728861ee30fe8d893f9c0a", "generation_seconds_batch": 20.123499057022855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3109968900680542, "target_z": -0.017578139462918224, "ce": 5.967014789581299, "genuineness": 4.2374773025512695, "identity": 0.4674288034439087, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8eda5c7024a38127d14bf19da82c8b9aab818f9763e7f85d9fae4485b9f87573.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "8fc0a9192e99cfe4a2fac0541607b992c0d55d7adefb4616f17f172cbdad1273", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7d0caa37ee34ab7def36f80d5b284b4da704148ca97670984d13b3bb0a6ed46c", "generation_seconds_batch": 16.29864923004061, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6599342823028564, "target_z": 2.187500024358599, "ce": 6.09409761428833, "genuineness": 3.9299514293670654, "identity": 0.6643369197845459, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8fc0a9192e99cfe4a2fac0541607b992c0d55d7adefb4616f17f172cbdad1273.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "8fcd6a8dbc88a540987b26aaa48afba1e31677a009172c0fbe7a457e15200a20", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9f0e2739bb6ce7ee8d5486aa2aed73cf66a72374df7621a81c4a8b6521f6d244", "generation_seconds_batch": 20.90115363697987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.814010739326477, "target_z": 0.8046874908655254, "ce": 6.221180438995361, "genuineness": 3.9048471450805664, "identity": 0.49174144864082336, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/8fcd6a8dbc88a540987b26aaa48afba1e31677a009172c0fbe7a457e15200a20.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "9027a469e8c5f4ec153c875b382261e03d442b59550da2aee8ad4219813dffc4", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "48d140a06a44ad015fa557f81eb28146e9832e7572dfbf083139460fba8dcfcb", "generation_seconds_batch": 22.444250102038495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08039909601211548, "target_z": -0.3945312606568871, "ce": 6.117925643920898, "genuineness": 4.256305694580078, "identity": 0.5627299547195435, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/9027a469e8c5f4ec153c875b382261e03d442b59550da2aee8ad4219813dffc4.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "9031e8950ab541266f6ed34265b189894957caadae130ad4a83c512c133662d3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ba9632a85b62cac5b7d986d7c2c82bb9c3624c1c39b76f58e2aebe5a84074975", "generation_seconds_batch": 23.198714300990105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06845101714134216, "target_z": -0.41406252131377425, "ce": 6.062326908111572, "genuineness": 4.482243061065674, "identity": 0.7827263474464417, "hypothesis": "J'ai trouvé J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/9031e8950ab541266f6ed34265b189894957caadae130ad4a83c512c133662d3.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "9044d511c5d1bd408700fcfe75244847be5347859dfe2e09f8984df9078fbe24", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1cdff8d24fd04352dd351425a074079194a8c1fae5ccc55fdd85279705c0b6ff", "generation_seconds_batch": 15.104398743947968, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1066848635673523, "target_z": -0.3515624969551751, "ce": 5.982900142669678, "genuineness": 4.68307638168335, "identity": 0.5545324683189392, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/9044d511c5d1bd408700fcfe75244847be5347859dfe2e09f8984df9078fbe24.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "90459982177ed0561afcfcf3941d778d9d1e252fd748958ed448e0a9d882fab0", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5c0dc447032118aceab5831c3bcebeac789eec28231e55fe4c55b308f1af74ac", "generation_seconds_batch": 22.48659148090519, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027827590703964233, "target_z": -0.4804687393431129, "ce": 5.990842819213867, "genuineness": 4.65797233581543, "identity": 0.5189803838729858, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/90459982177ed0561afcfcf3941d778d9d1e252fd748958ed448e0a9d882fab0.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "904fc6a63e3f94024d139e99a2cd6546baf7328ac281c4544b4f7ba205c04b9c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "7acd1d987736441e7aa2b5c5ad8ce8512b754c90569cd4eea8817d714bf76193", "generation_seconds_batch": 20.986956006032415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03619122505187988, "target_z": -0.46679689098533067, "ce": 6.006728172302246, "genuineness": 4.557555198669434, "identity": 0.5587755441665649, "hypothesis": "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_Fear/904fc6a63e3f94024d139e99a2cd6546baf7328ac281c4544b4f7ba205c04b9c.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "905d064c4ee71910ff99119973eb79c1a73d24bfa08ad945afd91074ecb72f8b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "20c243fa0db967166be40eb6a6a2b391c131611916a0b2c57ba88c7f0b98f756", "generation_seconds_batch": 16.537662933929823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.050528913736343384, "target_z": -0.4433593879405058, "ce": 6.221180438995361, "genuineness": 4.532451152801514, "identity": 0.7314040660858154, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/905d064c4ee71910ff99119973eb79c1a73d24bfa08ad945afd91074ecb72f8b.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "907624db3ffdd21287a1f14e5eaf45d34278257a07a184ba95abb73e94672436", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7e547066cdec32502b6d868c4cd20e80d1fadf63aa2043d98dff8eb8d0335682", "generation_seconds_batch": 21.977003172039986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14372389018535614, "target_z": -0.291015618149144, "ce": 6.23706579208374, "genuineness": 4.319066047668457, "identity": 0.5892887711524963, "hypothesis": "De deur staat nog open. Ik heb je jas op de op de stoel gelegd. Zeg maar 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_Fear/907624db3ffdd21287a1f14e5eaf45d34278257a07a184ba95abb73e94672436.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "913e2a6f882972aa5a335bdfd9fe612f8df0fbb3ea6d3695b7a34639f104c1f9", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "dbd954596da16822421e01de1120e0cba93166fb3ceaf0dd89fdfcdb5ab5963e", "generation_seconds_batch": 22.437770272023045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.296712875366211, "target_z": 1.5937500121792996, "ce": 5.871703147888184, "genuineness": 3.8044304847717285, "identity": 0.37423503398895264, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/913e2a6f882972aa5a335bdfd9fe612f8df0fbb3ea6d3695b7a34639f104c1f9.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "91b95b44bc45a227352bd1af845ddb42a72d97cb82c65534e0c7d890f95a86a0", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "df86292f7fcf11c8d9438ff24c484527c03ac6fc700a3370d68061a090e89a6b", "generation_seconds_batch": 16.221557909972034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37641260027885437, "target_z": 0.08935547731357, "ce": 5.871703147888184, "genuineness": 4.243753433227539, "identity": 0.2550490200519562, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/91b95b44bc45a227352bd1af845ddb42a72d97cb82c65534e0c7d890f95a86a0.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "922016032e7d810497cc862f5b0c069e69490a2e958580522163f50bda09bd92", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "067456822a812d9b5f6289c71cc1e4f1663a97ca7a58fcee8fcaaaf017e01a21", "generation_seconds_batch": 21.20648012193851, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9981184005737305, "target_z": 4.375000048717198, "ce": 5.871703147888184, "genuineness": 3.4623863697052, "identity": 0.4517397880554199, "hypothesis": "The 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_Fear/922016032e7d810497cc862f5b0c069e69490a2e958580522163f50bda09bd92.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "9227cbe42bcdf7c0c0d2a2a0464042e6f1fddfa3b0c3cc2d7c779da8daddb9e6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "678f62150b5f9c06214335d16f1d7c7eb528e8428594675216d0fc5b8b4a9bc5", "generation_seconds_batch": 15.308979631983675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06367179751396179, "target_z": -0.4218750060896498, "ce": 5.990842819213867, "genuineness": 4.7081804275512695, "identity": 0.6951542496681213, "hypothesis": "J'ai trouvé la petite boîte. Elle était elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/9227cbe42bcdf7c0c0d2a2a0464042e6f1fddfa3b0c3cc2d7c779da8daddb9e6.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "925434718ec758d008f19d8156a01a38c3e3dbed173f4c59194765d0a9f5d2cf", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e3f5639919b4ec63903e3f96edc55b8bc9fa1acbcb284d2eac13bf9ab1e9a1af", "generation_seconds_batch": 21.79202737205196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5393123626708984, "target_z": 3.6249999512828017, "ce": 5.756534099578857, "genuineness": 3.823258876800537, "identity": 0.49796223640441895, "hypothesis": "He encontrado la cajita. Estaba junto. La ventana. Vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/925434718ec758d008f19d8156a01a38c3e3dbed173f4c59194765d0a9f5d2cf.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "925658ebf3beb973bc193dcecdea0c1eda69a3e42057f8c42fa041418b1e685f", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "87790646c58932e8f0813c2313860a99b140ac9146427366e2a86b7b3b10a195", "generation_seconds_batch": 15.355206076055765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09593158960342407, "target_z": -0.36914063641809336, "ce": 5.784333229064941, "genuineness": 4.532451152801514, "identity": 0.5466101169586182, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/925658ebf3beb973bc193dcecdea0c1eda69a3e42057f8c42fa041418b1e685f.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "92a08867e236003a77403580a04caa37b64b1149c943aa4c0cdd3bbbe8d92c22", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "435d57e0fc0a9c48a5c0c87678aece0678d68b5cdc7ed8351e1ac30f2f5d08d0", "generation_seconds_batch": 16.09815986698959, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5917766094207764, "target_z": 0.4414062667465369, "ce": 5.426913261413574, "genuineness": 4.362998008728027, "identity": 0.4218670725822449, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/92a08867e236003a77403580a04caa37b64b1149c943aa4c0cdd3bbbe8d92c22.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": "92bf68124e8194427ce3d0e98258933bd96efa95e86072ca62c49410ea65f11c", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5165b1ed1d7961e743f5beba9a3b387ccf9c8de3a203d2d1e1d68d0e8c660fba", "generation_seconds_batch": 14.960317337070592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4734906852245331, "target_z": 0.2480468788060311, "ce": 5.839932441711426, "genuineness": 3.6977379322052, "identity": 0.40216922760009766, "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_Fear/92bf68124e8194427ce3d0e98258933bd96efa95e86072ca62c49410ea65f11c.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": "9348d0588e021e83007a9fa1ead61a0b9387c8f1801a67991f292fec92cd9597", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5e2fb89153248abae9ad7400ce39bf870a99f25df128a61ec8a6ba8113c3c66b", "generation_seconds_batch": 18.08747296803631, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1055437326431274, "target_z": 1.2812500365378987, "ce": 6.086154937744141, "genuineness": 4.394378662109375, "identity": 0.5542829036712646, "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_Fear/9348d0588e021e83007a9fa1ead61a0b9387c8f1801a67991f292fec92cd9597.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "939ed089924eedb495fa8c40ff790ac91b46c87c19a79828fbbd10d9943830bc", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6b2c4a13cc1874bde754e033723e8252dfdde38e21d3865d1002cbba843353d1", "generation_seconds_batch": 20.87098663195502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5775461196899414, "target_z": 3.687499829489806, "ce": 5.95112943649292, "genuineness": 3.5063188076019287, "identity": 0.45509809255599976, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/939ed089924eedb495fa8c40ff790ac91b46c87c19a79828fbbd10d9943830bc.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": "93dd1759eb02ad756be2d8853ff965d762ffc8a39b1de9632e31103849cf63e5", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ee5428f8b75c5914206c2e6261799f5812c4f0dcdc4b6223c70bfb39247eb2a", "generation_seconds_batch": 18.577361867995933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7423223257064819, "target_z": 0.6875000243585991, "ce": 6.09409761428833, "genuineness": 4.400654315948486, "identity": 0.612464427947998, "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_Fear/93dd1759eb02ad756be2d8853ff965d762ffc8a39b1de9632e31103849cf63e5.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "9463d44bf57694b69167b940b468edaab94a189eea986b9d67120869b4422495", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d387d8595811fe4566b9aba4553e4b1e524399f2535019a4f6ca223fc2195e23", "generation_seconds_batch": 20.409418931929395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2680375576019287, "target_z": 1.5468751035240462, "ce": 6.133810997009277, "genuineness": 3.9927117824554443, "identity": 0.79674232006073, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/9463d44bf57694b69167b940b468edaab94a189eea986b9d67120869b4422495.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "947ab7d3f38f16ec7b4e20a18d1ff7396f8fdbe7b8c1d224267e2c866abe5582", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "bb9a254db7a183c41bae2450775deb1117e21798ac64eae6384e4aa816a38bf9", "generation_seconds_batch": 15.500296029960737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5284518003463745, "target_z": 0.33789059988019465, "ce": 5.784333229064941, "genuineness": 4.645420074462891, "identity": 0.7718347311019897, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/947ab7d3f38f16ec7b4e20a18d1ff7396f8fdbe7b8c1d224267e2c866abe5582.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "94a40dd846d9aa716ab1dd738f9233395d169eda44b0b4452b4702ba45d91fa3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "182eb180a5c13f4bcf2c7171996857645d4442bde8961a8e4a83e660ef96d79b", "generation_seconds_batch": 16.058046050020494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5224777460098267, "target_z": 0.328124945193152, "ce": 6.09409761428833, "genuineness": 4.582659721374512, "identity": 0.7365440130233765, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/94a40dd846d9aa716ab1dd738f9233395d169eda44b0b4452b4702ba45d91fa3.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "94d374b854f4cdc3338b46b1c82adec2cdffdd75c19668f95dc3b3dff1f76ced", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0c3596a6d5694c902f0d04c5d3dad644a7a9ebca630351c64d6ca063a8773355", "generation_seconds_batch": 21.20726532500703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16762003302574158, "target_z": -0.2519531211939689, "ce": 5.855817794799805, "genuineness": 4.494794845581055, "identity": 0.5476511716842651, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/94d374b854f4cdc3338b46b1c82adec2cdffdd75c19668f95dc3b3dff1f76ced.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "94d8ecc85f9646e6db86f4eeee0d0cca7bebd530f6ec273e8898de3508a0a8b8", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "fab80eb85a99eee579fa56fb1c42744fd71a909b2a777dd39f457a95fb49cbce", "generation_seconds_batch": 22.86590414494276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4448689222335815, "target_z": 1.8359374299690276, "ce": 5.387199878692627, "genuineness": 4.030367851257324, "identity": 0.5495846271514893, "hypothesis": "J'ai trouvé la 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_Fear/94d8ecc85f9646e6db86f4eeee0d0cca7bebd530f6ec273e8898de3508a0a8b8.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": "94ef2c8b7b5a5e9c2899e7f928be90225a85448fb7a4fdd5155991fca41d86ba", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b5210ec3e15e2a78ef269b07c5ba7a74328ee735900258e8b4a50771054fed31", "generation_seconds_batch": 22.00773494306486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.979001522064209, "target_z": 4.343750109613696, "ce": 5.244231700897217, "genuineness": 3.5816311836242676, "identity": 0.48995983600616455, "hypothesis": "Tischlüsse liegen auf dem Küchtentisch. Ich suchte in der Schublade dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.14285714285714285, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/94ef2c8b7b5a5e9c2899e7f928be90225a85448fb7a4fdd5155991fca41d86ba.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "95278d4e59e4abaf130548a6170c850b54d67fbe8afa2f6d3c226e6cf9f73136", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7058e617c0fb47d7c1d0cc233d08ac6de19daa546c88723764cd8140368bb807", "generation_seconds_batch": 21.755733020952903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8044523000717163, "target_z": 0.7890625213137742, "ce": 5.855817794799805, "genuineness": 4.494794845581055, "identity": 0.5608327984809875, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/95278d4e59e4abaf130548a6170c850b54d67fbe8afa2f6d3c226e6cf9f73136.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "959415a12fd0e6cc8570b1923e585a4792c459838763e3a507e502ee6b151eb8", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "df699169b3a7ed2bb86425c5c2a6b0251a991c5b874eb2e7f1b4642784b87535", "generation_seconds_batch": 23.37935300404206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.621700406074524, "target_z": 2.1249999512828017, "ce": 6.0146708488464355, "genuineness": 4.457139015197754, "identity": 0.7044169902801514, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de là, des vieilles fenêtres. 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_Fear/959415a12fd0e6cc8570b1923e585a4792c459838763e3a507e502ee6b151eb8.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "95950b3712c1ec6d4414acbdd38b4cd44b4392534d429f61d5290dcdedeff617", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4b862c78d04a3b5ea1603991d91e7f9189a33343af9ab8830d0c3bb10d187b13", "generation_seconds_batch": 22.02204328496009, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06964585185050964, "target_z": -0.4121093514026071, "ce": 6.24500846862793, "genuineness": 4.545003414154053, "identity": 0.7132267951965332, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/95950b3712c1ec6d4414acbdd38b4cd44b4392534d429f61d5290dcdedeff617.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "95db7d8d6f8c1de677d061f7903e0799a3f8e1ffc8585983dcbcc3d0ef7ecfc0", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "771341bb43380e7dcf45bef75ab225b5770aaf1f65bae9f34eae28f38c8a81a1", "generation_seconds_batch": 22.485209417995065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8355172872543335, "target_z": 0.8398437697913618, "ce": 6.062326908111572, "genuineness": 4.218649387359619, "identity": 0.2393397092819214, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/95db7d8d6f8c1de677d061f7903e0799a3f8e1ffc8585983dcbcc3d0ef7ecfc0.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": "9601ae68ea664b03ee08a4ba8c8903c5f71c36bab42133796c3ea4fa826189e2", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e3008e1b926eec74b8677743bc5fe8e0fae9e05d202e077c05a70869bfb69e4e", "generation_seconds_batch": 15.750365309068002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1198813915252686, "target_z": 1.3046874908655253, "ce": 5.19657564163208, "genuineness": 3.7667744159698486, "identity": 0.45145413279533386, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherrekal. Wir stellen ihn nach dem Essen zurück.", "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_Fear/9601ae68ea664b03ee08a4ba8c8903c5f71c36bab42133796c3ea4fa826189e2.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "9679de339b7be4ce2db660852cf4ccf4893e6710a331f71a58a6424a73acb368", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "42aef62ee08272c0796cd9b2cbcb5ddb684388197809c3553eeb179fceaf4185", "generation_seconds_batch": 22.10605249798391, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8044523000717163, "target_z": 0.7890625213137742, "ce": 5.959072113037109, "genuineness": 4.444586753845215, "identity": 0.5355979204177856, "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_Fear/9679de339b7be4ce2db660852cf4ccf4893e6710a331f71a58a6424a73acb368.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "967ecdd6b1e0835dc67f595db8cdba1f0b7863e6461d14f90ba00e37929acf83", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4bc428e2877e17badf14cdab5f9d7dad8a8f422bb6767dd5b2c4bfd883aa1cdc", "generation_seconds_batch": 21.874762470950373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.673130750656128, "target_z": 3.8437499147449032, "ce": 5.855817794799805, "genuineness": 3.5941832065582275, "identity": 0.09077996760606766, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/967ecdd6b1e0835dc67f595db8cdba1f0b7863e6461d14f90ba00e37929acf83.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "96dc9cf93877368b06b92c59e621fae7aec547158df9082f0c1be48235622d48", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "dd17ba09baddd75f2a64abf72e7c683ce99aa612d22d5eeec22ba55fdf624fe1", "generation_seconds_batch": 20.17376328399405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42629578709602356, "target_z": 0.17089842113406623, "ce": 6.062326908111572, "genuineness": 3.9801597595214844, "identity": 0.6083550453186035, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/96dc9cf93877368b06b92c59e621fae7aec547158df9082f0c1be48235622d48.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": "96dd3eab61893d65d2596dc94121dda50905f7cbd6608b0d5d228224be71a3e6", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7f0b852d86211dbf6e743b3ff0ffb534747c2767bd5a3dba387f175773d9dbd9", "generation_seconds_batch": 18.577361867995933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3138345777988434, "target_z": -0.012939433999693667, "ce": 5.959072113037109, "genuineness": 4.432034492492676, "identity": 0.5641803741455078, "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_Fear/96dd3eab61893d65d2596dc94121dda50905f7cbd6608b0d5d228224be71a3e6.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "96fd23c871be8b26b6cf1dd44461fb7e0c0e38a5946a7a0d92f2b8d5550cba0f", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "43dadc9fbab7c80b8f304e8ddc21004fea63ed069fca779479c4b7b99de64010", "generation_seconds_batch": 21.61805590800941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02065873146057129, "target_z": -0.49218751522412446, "ce": 6.181467056274414, "genuineness": 4.8588056564331055, "identity": 0.7049320936203003, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/96fd23c871be8b26b6cf1dd44461fb7e0c0e38a5946a7a0d92f2b8d5550cba0f.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": "9715f97abd2e4bbfc95988b5fa527df8218618d62265ba5943b225025dd967cc", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "011cdd4b8817b6d9de1e911c1538ccac3e6ff33548fc421f347b0d1f8a0b1096", "generation_seconds_batch": 21.8380950599676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.434169292449951, "target_z": 3.4531248964759538, "ce": 5.621508598327637, "genuineness": 3.603597402572632, "identity": 0.7269871830940247, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/9715f97abd2e4bbfc95988b5fa527df8218618d62265ba5943b225025dd967cc.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "97a1669936bbf2d2701a94a43f8d8825a19f7907b92707bbdfa9d25e4b8ec5b0", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ffb23a323a77ed31aa5b345c384a6ce5ad4a749d81d489b284828b31d2079f99", "generation_seconds_batch": 22.44767971104011, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0481393039226532, "target_z": -0.4472656303284436, "ce": 6.1894097328186035, "genuineness": 3.8169827461242676, "identity": 0.3963492214679718, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/97a1669936bbf2d2701a94a43f8d8825a19f7907b92707bbdfa9d25e4b8ec5b0.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "97b0d7b18066f4ef1b57f5d891cae57d42966ef051cca3da88ca73613f2869b6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0f5c274c7324a87f112245ab6222b36625285b601c633ad4ff24a96e99148000", "generation_seconds_batch": 20.183506205910817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6969196796417236, "target_z": 0.6132813215533849, "ce": 6.109982967376709, "genuineness": 4.068024158477783, "identity": 0.6122468709945679, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/97b0d7b18066f4ef1b57f5d891cae57d42966ef051cca3da88ca73613f2869b6.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "97cb1e4ade877413a75cbff06209b7f9198a8521aabef31cbb92a9ade5f9b2c8", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2d08f91bc13f3d921a587a156a492a72767248cf5f95a9f9bb2232dd3befe08a", "generation_seconds_batch": 22.1630537789315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3556528091430664, "target_z": 0.05541990522361389, "ce": 5.935244083404541, "genuineness": 4.243753433227539, "identity": 0.40849897265434265, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/97cb1e4ade877413a75cbff06209b7f9198a8521aabef31cbb92a9ade5f9b2c8.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "98a1662697cb60f75364f5fa77602a2c2d42c5123fab33ac8f45bceff27ff53d", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "cb3f792ebdc495e8d82207408523b8dee6b8337517a4461fa84727dca176616b", "generation_seconds_batch": 21.938596609048545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9143745303153992, "target_z": 0.9687499634621013, "ce": 5.661221981048584, "genuineness": 4.532451152801514, "identity": 0.7231742739677429, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/98a1662697cb60f75364f5fa77602a2c2d42c5123fab33ac8f45bceff27ff53d.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "98a8378f24656bf83e83777377f1d1987a16f1317f77f5661ef62d93938a2319", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "27b9ceb54a2e8e5eaceb71a5d174925633e50ec35b6caaa2c295a9656340cfe8", "generation_seconds_batch": 22.65324461599812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15806157886981964, "target_z": -0.2675781151043191, "ce": 6.0305562019348145, "genuineness": 4.281409740447998, "identity": 0.40726613998413086, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/98a8378f24656bf83e83777377f1d1987a16f1317f77f5661ef62d93938a2319.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "98cb6aeb333b1ad7d0300007128b5481e3e6eaec2bf50097e61ac45d63479a58", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1fa767321b1d7b45d86e97bed92649fd5d6befc11ae28e1d092ee6c79ae58d84", "generation_seconds_batch": 20.93115697999019, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8235691785812378, "target_z": 0.8203124604172765, "ce": 6.022613525390625, "genuineness": 4.15588903427124, "identity": 0.6167107820510864, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude graam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/98cb6aeb333b1ad7d0300007128b5481e3e6eaec2bf50097e61ac45d63479a58.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": "9970d5c66d08d0cc7fd2de1386dca8854f57d3ea8eb9aa4addcfa406ecc8187c", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8dfab4c1200df4ffd27165d10f23cdd73a9197af7836ad0a9ee3c41d870712f0", "generation_seconds_batch": 16.087857979000546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.329026222229004, "target_z": 3.281249841669106, "ce": 5.855817794799805, "genuineness": 4.011539936065674, "identity": 0.6963751316070557, "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_Fear/9970d5c66d08d0cc7fd2de1386dca8854f57d3ea8eb9aa4addcfa406ecc8187c.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "b08f1dbe46032054b0da59a874aca6e9bd589780a9a1eba13e34377103a0a389", "generation_seconds_batch": 15.78217855503317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0768146812915802, "target_z": -0.4003906242387938, "ce": 6.475345611572266, "genuineness": 4.796044826507568, "identity": 0.6791036128997803, "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_Fear/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "9a19bceec0b0ab98c7c88045f1ce530e7c05a32cb60e267bbe4e38d9bc52492e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "5a416d43be8b082a439cd8315a9eb285d6c667ddbdb83e0ed9621e2690eaddc5", "generation_seconds_batch": 21.45383932197001, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6562961935997009, "target_z": 0.5468750060896498, "ce": 6.117925643920898, "genuineness": 4.243753433227539, "identity": 0.6147060394287109, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist. Hol den Funaunes erhublich.", "wer": 0.21052631578947367, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/9a19bceec0b0ab98c7c88045f1ce530e7c05a32cb60e267bbe4e38d9bc52492e.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "9a7bb493165763b4824a254d172f84d68d4ab5f34d32c57dfe9ad4e48d21c7b5", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f7fc74e50363df7f2409d88b13e13ebdd3d87bacb4d5e0449517f9a753b6b341", "generation_seconds_batch": 16.537662933929823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013489902019500732, "target_z": -0.5039062423879378, "ce": 6.372091293334961, "genuineness": 4.545003414154053, "identity": 0.5816830396652222, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/9a7bb493165763b4824a254d172f84d68d4ab5f34d32c57dfe9ad4e48d21c7b5.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "9adc6896e73b487deeb3832efcf22c11fe6da7f3d6839da38f472cfd590832f8", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c15f793746fd8cb257081e375660a4e02b1bde47e413f1df4393ebe2fa24187b", "generation_seconds_batch": 22.140452536055818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5045557022094727, "target_z": 0.2988281760008169, "ce": 6.300607204437256, "genuineness": 4.369274139404297, "identity": 0.6755343079566956, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude. Naast het oude. We kunnen er samen in kijken.", "wer": 0.16666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/9adc6896e73b487deeb3832efcf22c11fe6da7f3d6839da38f472cfd590832f8.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "9b97f817a4143a9ad87e8767d2fbfc5f00fe6643beec915891cdbf4934b1f484", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0e048c9b82d074db2a7c0f8b5183f0356b29caadc9a3388ada3e840a74a3abaf", "generation_seconds_batch": 22.150334041099995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3922975063323975, "target_z": 1.7500000974343966, "ce": 5.601652145385742, "genuineness": 3.9048471450805664, "identity": -0.007864134386181831, "hypothesis": "De deur staat toch open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/9b97f817a4143a9ad87e8767d2fbfc5f00fe6643beec915891cdbf4934b1f484.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "bcfb23528daf78719100fd0944c6b9ebd0fd6d6bd85803e0d96cadd42fa1263d", "generation_seconds_batch": 15.610990668996237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05411332845687866, "target_z": -0.43750002435859914, "ce": 6.213237762451172, "genuineness": 4.369274139404297, "identity": 0.7737869024276733, "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_Fear/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "c6ca003bf3c4900d410b962f40cc30ebbc3e46a1106c630eb7482bdd161fcc88", "generation_seconds_batch": 13.259259195998311, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3072631359100342, "target_z": -0.023681624925121665, "ce": 6.1020402908325195, "genuineness": 4.262581825256348, "identity": 0.5274170637130737, "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_Fear/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.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": "9d20bac27de1aca73fab73eb05cc39f61f9697247e2ebebfc67dd6f713b590dd", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cdf93a461fb9c1947573b403a08d29d5025b85331cf6196330ca6796fb965a82", "generation_seconds_batch": 14.960317337070592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9466880559921265, "target_z": 2.6562500852550968, "ce": 5.704906940460205, "genuineness": 3.4341442584991455, "identity": 0.0007513724267482758, "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_Fear/9d20bac27de1aca73fab73eb05cc39f61f9697247e2ebebfc67dd6f713b590dd.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "9d2ae86f357f6139af0a01732296802cb9f631df3d2d268be9db36788c12aadb", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "13119e832e94adb072a27cb9f1075d5be485eee9a47fab36deb85ad9383db3f9", "generation_seconds_batch": 22.39672655495815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4186904430389404, "target_z": 5.062499878207005, "ce": 5.6334228515625, "genuineness": 3.8546390533447266, "identity": 0.7018147110939026, "hypothesis": "Ich hatte 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_Fear/9d2ae86f357f6139af0a01732296802cb9f631df3d2d268be9db36788c12aadb.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "9d6c8f088c1ed7ea5aade2df20f5202380f8b0e2015090d8b1dfb79dc8316b63", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1a7c44dd730cf8ffdb9775c31d81111f26b1a4a549698efbfe6f9b5ea40c615e", "generation_seconds_batch": 24.813716487959027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07323026657104492, "target_z": -0.40624998782070043, "ce": 6.205295085906982, "genuineness": 4.607763767242432, "identity": 0.5056747794151306, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/9d6c8f088c1ed7ea5aade2df20f5202380f8b0e2015090d8b1dfb79dc8316b63.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "9da0d334a9179569e34d073decde016edb3ebd1ce353b2b45e5a3cb911576c14", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a7abb318004cbbca944ebb8bed3545e01e35142042f0aabf0830adb66090ec0c", "generation_seconds_batch": 20.805961609934457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2237759679555893, "target_z": -0.16015625456723734, "ce": 5.967014789581299, "genuineness": 4.444586753845215, "identity": 0.4416463375091553, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/9da0d334a9179569e34d073decde016edb3ebd1ce353b2b45e5a3cb911576c14.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": "9dc8145174cb449afe3409997773ed2d50abe2a517e69dc9c2b3d2af29e4243c", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0a0e30cb2559877a460bc4bf4cd9e00f124fc4601c48915432a837c77cd8bbf5", "generation_seconds_batch": 23.521791590959765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.663572311401367, "target_z": 3.828124945193152, "ce": 6.086154937744141, "genuineness": 3.7416701316833496, "identity": 0.5414317846298218, "hypothesis": "The road turns left, behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/9dc8145174cb449afe3409997773ed2d50abe2a517e69dc9c2b3d2af29e4243c.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "9dd4be880ca37a0d1d33d90a0882389a44bc4a5a3b09b485149a9eccdbb978c1", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "127d8341fc3339b85c1075867e01384ad78e3b49dca4d9cbcd789dbb3b9f2600", "generation_seconds_batch": 21.490834222058766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.001541823148727417, "target_z": -0.5234375030448248, "ce": 6.038498878479004, "genuineness": 3.886019229888916, "identity": 0.40176814794540405, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/9dd4be880ca37a0d1d33d90a0882389a44bc4a5a3b09b485149a9eccdbb978c1.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "9e45fbbb42f8b6a30fc8796222198ed399f02e780b43201bca410ae29eb48987", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7a6f47454abced8d0d94b82a3f60b9364a47ad2095f3f98c3ecb7b2d40bcc4a9", "generation_seconds_batch": 16.585426885052584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08517833054065704, "target_z": -0.3867187515224124, "ce": 6.109982967376709, "genuineness": 4.595211505889893, "identity": 0.5777773857116699, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/9e45fbbb42f8b6a30fc8796222198ed399f02e780b43201bca410ae29eb48987.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "9e68c93f5d09f565217fd2a44f920facf05f4c78582fd6940f31f1bc3d7d124c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "66e1889bd0df47b23c084ee134616ac28b3d54a2b89f1515c35fe5ad22b8fb22", "generation_seconds_batch": 15.295291983056813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11743812263011932, "target_z": -0.333984381850856, "ce": 6.117925643920898, "genuineness": 4.582659721374512, "identity": 0.5614509582519531, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/9e68c93f5d09f565217fd2a44f920facf05f4c78582fd6940f31f1bc3d7d124c.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "9f20773c088998d66404c2a289c4d17a730bf2b20510c5df11f892989e721fe1", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0b17f024afa0134ed0a9d3a8372e71f646a75403436f67d92a634f2caabbbe7c", "generation_seconds_batch": 22.242242051986977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6025835275650024, "target_z": 2.0937500121792993, "ce": 5.784333229064941, "genuineness": 3.973883628845215, "identity": 0.5879756212234497, "hypothesis": "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_Fear/9f20773c088998d66404c2a289c4d17a730bf2b20510c5df11f892989e721fe1.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "9f9a4e4f2f03fce970d8dc03fdfa378cc1a8a31d34024cabe3acb9d7fb986f5a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e12a26f0f214119844b9bc17bd72c3619cf844221a235c80c91c5234f54c4fa6", "generation_seconds_batch": 23.55888942000456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4569244384765625, "target_z": 5.125000146151595, "ce": 5.343515396118164, "genuineness": 3.4937667846679688, "identity": 0.5582106113433838, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce cas-là contient.", "wer": 0.10526315789473684, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/9f9a4e4f2f03fce970d8dc03fdfa378cc1a8a31d34024cabe3acb9d7fb986f5a.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": "9fe78ebd8e0ca9b11130de3ba35167d5245c1858aa826f7b56815cf0c958b1cb", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e82d5e92890a06084f55e2e1008247449d24ac1d652b1732a2868abd811654d5", "generation_seconds_batch": 19.947469540056773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.759049654006958, "target_z": 0.71484381850856, "ce": 5.959072113037109, "genuineness": 4.344170093536377, "identity": 0.6480859518051147, "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_Fear/9fe78ebd8e0ca9b11130de3ba35167d5245c1858aa826f7b56815cf0c958b1cb.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "a1639aab59af050cd5364369ac7756330c9b9fac9efad4553e3832031f468b95", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "96dd1045e38c0b6737495f651ad75216251b7906446701bfd9ae898c706ed7db", "generation_seconds_batch": 21.472937868908048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07442507147789001, "target_z": -0.40429686662673153, "ce": 6.284721851348877, "genuineness": 4.2751336097717285, "identity": 0.5107316374778748, "hypothesis": "ik heb het kleine doosje gevonden het stond naast het oude raam we kunnen er samen in kijken", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a1639aab59af050cd5364369ac7756330c9b9fac9efad4553e3832031f468b95.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "a17b4dd843ba26dd8d34ca1910790d1577cebf7879630eaaaf3d47ffe75a42ee", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7f3822ed5e9f890d1220bc51d937e9536f8b05a7d7ac92d8e6eb80bffbfef6c7", "generation_seconds_batch": 16.373578864964657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0805063247680664, "target_z": 2.874999853848405, "ce": 5.919358730316162, "genuineness": 4.105680465698242, "identity": 0.4977186322212219, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a17b4dd843ba26dd8d34ca1910790d1577cebf7879630eaaaf3d47ffe75a42ee.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "a21887ca97a1c96668fbba0981056a7936a4a58b3396c448179ff638f9a17c1c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d52ba8deca9e6df20495ec9d3d6b1490647109f312016ee0139a1270e5a16094", "generation_seconds_batch": 20.130269059096463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21541231870651245, "target_z": -0.17382812728361866, "ce": 5.879645347595215, "genuineness": 4.319066047668457, "identity": 0.5188494920730591, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a21887ca97a1c96668fbba0981056a7936a4a58b3396c448179ff638f9a17c1c.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "a2316e7865a44d8de6d937fd91c5c06bf62e74b67d8309630c2338d8325c1c95", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "14073f3484b047da2da5ade053c33bd1314920fd70ba56135025e9944256ed9b", "generation_seconds_batch": 21.17353564000223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.625338554382324, "target_z": 3.7656250669861477, "ce": 5.677107334136963, "genuineness": 3.390212059020996, "identity": 0.5838582515716553, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a2316e7865a44d8de6d937fd91c5c06bf62e74b67d8309630c2338d8325c1c95.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "a3237c02266e1be063ee5ae65393453dbd4ba320c130c03867a8f9f0cebcf80c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b029c8f318c3f82588d815243e161215cbe5bec4651c84b1c5d80b6af7f1e2b2", "generation_seconds_batch": 22.30231169704348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1365550458431244, "target_z": -0.3027343696715564, "ce": 5.895530700683594, "genuineness": 4.432034492492676, "identity": 0.48540759086608887, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a3237c02266e1be063ee5ae65393453dbd4ba320c130c03867a8f9f0cebcf80c.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "a328fe3c04936eade70d0d9b536515d149240eae2a966189847765665d3a56a5", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c4139936a1e926cc6be395d5277ddfe82f9c2811d41b4f82254b4beeb26cf2ab", "generation_seconds_batch": 20.887526395963505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32847094535827637, "target_z": 0.010986312805724777, "ce": 5.879645347595215, "genuineness": 3.9927117824554443, "identity": 0.4383610785007477, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a328fe3c04936eade70d0d9b536515d149240eae2a966189847765665d3a56a5.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "a3c63601753c5ff7d80a34597e7d4eeaef1cbe6b562336249d6e8d0632528077", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "18c100ab591d85c03aea8ac63ad0f167ebae0d9fcedef95e3a67b9b50c939d09", "generation_seconds_batch": 15.736237279954366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01518547534942627, "target_z": -0.5507812484775876, "ce": 6.268836498260498, "genuineness": 4.344170093536377, "identity": 0.47320064902305603, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a3c63601753c5ff7d80a34597e7d4eeaef1cbe6b562336249d6e8d0632528077.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "a3d53bc432d0c34621d724a1fbed2f8436048564da0a00351266acc331a3fbb0", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "07abb2ffc628f55e8af29a3cf873a8ff04c7ba8e46c6635cab3fd34d72d48e52", "generation_seconds_batch": 21.691769947996363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.864300012588501, "target_z": 4.156250085255097, "ce": 5.990842819213867, "genuineness": 3.6067352294921875, "identity": 0.48564016819000244, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a3d53bc432d0c34621d724a1fbed2f8436048564da0a00351266acc331a3fbb0.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "a3e9808c83d6a31b373a443095760e167686723531fdac5a44edf0cf3669a804", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3d139e990e3516d1deb50280d050445e0eb180d919a778aaf182a9fff44bac51", "generation_seconds_batch": 22.020389165030792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8355172872543335, "target_z": 0.8398437697913618, "ce": 5.7128496170043945, "genuineness": 4.055472373962402, "identity": 0.4926050305366516, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a3e9808c83d6a31b373a443095760e167686723531fdac5a44edf0cf3669a804.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "a40a334ea120c64124e7dbaf4556558fb66e50b05087dfb2d8e1cd7ffb599cad", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e4db59f71ad95c1aba106ccfc2f2c6672ba91c2ed75544ec56e7e921b206609b", "generation_seconds_batch": 21.234881995012984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6754131317138672, "target_z": 0.5781250426275485, "ce": 5.550024509429932, "genuineness": 4.068024158477783, "identity": 0.6670917272567749, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a40a334ea120c64124e7dbaf4556558fb66e50b05087dfb2d8e1cd7ffb599cad.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "a4a17a7694ad5f5c4740999f117dee2435f4b886438674bb27de33e6348496a4", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8be522a9a4ce835e67562c2e802b77b0ff874d90bc850e5da9e34393ee6bd903", "generation_seconds_batch": 17.611082619056106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4628448486328125, "target_z": 3.500000194868793, "ce": 5.998785495758057, "genuineness": 4.017816066741943, "identity": 0.031064417213201523, "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_Fear/a4a17a7694ad5f5c4740999f117dee2435f4b886438674bb27de33e6348496a4.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": "a4c12ab8a1abd680962767782ff5fecf69fa2e9eddeaa20cb5e208c02ed204b8", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "df45dea06ec28cd808f91f730cfc5f03013956994d6d548b762bc9055bfadb4d", "generation_seconds_batch": 16.22633032500744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09473678469657898, "target_z": -0.3710937576120622, "ce": 5.974957466125488, "genuineness": 4.570107460021973, "identity": 0.6497604250907898, "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_Fear/a4c12ab8a1abd680962767782ff5fecf69fa2e9eddeaa20cb5e208c02ed204b8.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": "a51287111cd576890bd4802805e58a8c74f5b6687465ebc4bf040bd4c299be58", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0a2f51cd6dcb9f39c4c27a30be47deefdc440a611d7e3a44be111c90f5106196", "generation_seconds_batch": 17.80264463298954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.253699779510498, "target_z": 1.5234374543276266, "ce": 6.09409761428833, "genuineness": 3.8797430992126465, "identity": 0.11959626525640488, "hypothesis": "De sleutels liggen op de keuktafel. Ik kijk in de la. En daarna, naast het raam, mis ze mee als je weggaat.", "wer": 0.13636363636363635, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a51287111cd576890bd4802805e58a8c74f5b6687465ebc4bf040bd4c299be58.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "a5438bc42cbf23c20b3916bb735bd9d2390eebbfd31cc1fbaed7536ba73470c6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "43972087fba5da51d7987667dd61050fea35d9f50076daeb40aee2b0d874c5ac", "generation_seconds_batch": 21.085711285937577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15567195415496826, "target_z": -0.271484381850856, "ce": 6.372091293334961, "genuineness": 4.7458367347717285, "identity": 0.8226228952407837, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a5438bc42cbf23c20b3916bb735bd9d2390eebbfd31cc1fbaed7536ba73470c6.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": "a5bf0ad2dec92ba8234ada02fa3d3a870c115f82af9b5e0f2fcc7b08f7e687bf", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "468a58f384f0cabe8a8084e2d2a5bba9d6bd6e14dc975f0d66ff1ac6a9b047ab", "generation_seconds_batch": 21.06732575793285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0327141284942627, "target_z": 2.7968750060896497, "ce": 5.903473377227783, "genuineness": 4.162164688110352, "identity": 0.5809553265571594, "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_Fear/a5bf0ad2dec92ba8234ada02fa3d3a870c115f82af9b5e0f2fcc7b08f7e687bf.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "a67141a942a6d250ae0c99c02ef668df1d7cd51bba349a2bec24e7ddd7cd2954", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0a0aa4ae8f442e46bd594925cae7f1094ea986e6c294ba349a56530b8aad7145", "generation_seconds_batch": 16.83027221111115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4066351652145386, "target_z": 1.7734375517620231, "ce": 5.903473377227783, "genuineness": 3.9801597595214844, "identity": 0.059126030653715134, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a67141a942a6d250ae0c99c02ef668df1d7cd51bba349a2bec24e7ddd7cd2954.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": "a69b9cd21e7c5b64fd5ecfe053fbb9b46b8cc73bec53b3464f49406181a0010e", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9a40d2c8a4b897ffc2911c10260d120709e81569f5892664a10b0296fd5f96a8", "generation_seconds_batch": 16.23187083809171, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0363521575927734, "target_z": 4.437499926924203, "ce": 5.863759994506836, "genuineness": 3.8420867919921875, "identity": 0.5410031080245972, "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_Fear/a69b9cd21e7c5b64fd5ecfe053fbb9b46b8cc73bec53b3464f49406181a0010e.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "a767b3ddec5b49e29acc516ec32833339fa8c09dedbd3a7c00eba6fbb0fbab0e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "65a0c2ba3b33cbc2378071fd3a59de00f623ea6a887fef2ac0cccf010de0c4b8", "generation_seconds_batch": 21.077260173973627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.017235279083252, "target_z": 4.406249987820701, "ce": 5.982900142669678, "genuineness": 3.6914620399475098, "identity": 0.5499362945556641, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a767b3ddec5b49e29acc516ec32833339fa8c09dedbd3a7c00eba6fbb0fbab0e.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "a77a0d0ca7682fc39356af42dcf4926dc68d250a4505cf351e99ef634fcf9b8e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3a84aee0d453eb5a71f0a8a62d03f01644cf4672c77804d1b2460c553cbe2829", "generation_seconds_batch": 20.409418931929395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3492844104766846, "target_z": 1.6796875395827235, "ce": 5.708878040313721, "genuineness": 4.024092197418213, "identity": 0.544880747795105, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a77a0d0ca7682fc39356af42dcf4926dc68d250a4505cf351e99ef634fcf9b8e.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "a7a141f8e14d0a01522e149e63eb0374906a5d3806e785a915f79cfb4c5b3b5c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f1da8282e88727c86361d276b722dd0c7e5635340fb6219fbac187d93d6870b4", "generation_seconds_batch": 21.733973794966005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11385370790958405, "target_z": -0.3398437454327627, "ce": 6.006728172302246, "genuineness": 4.256305694580078, "identity": 0.5841223001480103, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a7a141f8e14d0a01522e149e63eb0374906a5d3806e785a915f79cfb4c5b3b5c.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "a847db00c1fc8d190a9e04f90dd320f7afea958024b6a9f6e5cfd65a879a548e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "78f6a31db9d2c615bcdc62139a12b95216ae4db69498ac714dcf8dfd155405ac", "generation_seconds_batch": 15.276812607073225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3970767259597778, "target_z": 1.757812582210272, "ce": 5.281959533691406, "genuineness": 3.9676074981689453, "identity": 0.5729170441627502, "hypothesis": "La porte 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_Fear/a847db00c1fc8d190a9e04f90dd320f7afea958024b6a9f6e5cfd65a879a548e.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "a875b1b814c4ff358ea6fd59e393f657f44fa3e285c1f9b686e67e542fa4981f", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "57bb9435399ca9801d525ed6ff1e939249d19c8dd8b421693f8898c776050ff7", "generation_seconds_batch": 22.437770272023045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0709481239318848, "target_z": 2.85937527403424, "ce": 6.022613525390625, "genuineness": 3.8546390533447266, "identity": 0.7501353025436401, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a875b1b814c4ff358ea6fd59e393f657f44fa3e285c1f9b686e67e542fa4981f.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "a87ace535ce6bb7751035d4537b0be3b296468af08825129a3e8d514c47716c7", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "702d50abd1f43eeb20160c5e45b6624ad9c7693419d3ccd1ad5d9dac9bbc7b03", "generation_seconds_batch": 26.739957237034105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.483102798461914, "target_z": 1.8984375030448248, "ce": 6.046441555023193, "genuineness": 3.7918784618377686, "identity": 0.6152791976928711, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a87ace535ce6bb7751035d4537b0be3b296468af08825129a3e8d514c47716c7.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "a8a5a5566efe2a808420374da0a4ec8440399c3f207609cf5e6eb645c61b4bd7", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3f9f3682526d685639f0fad1bea2d55f34d025b65455ed93ca9861173c8f5830", "generation_seconds_batch": 23.52511707902886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1628407984972, "target_z": -0.2597656303284436, "ce": 6.117925643920898, "genuineness": 4.143336772918701, "identity": 0.6085070371627808, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a8a5a5566efe2a808420374da0a4ec8440399c3f207609cf5e6eb645c61b4bd7.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": "a8b465fd8e20e3cf1994b1af05227058872700352a24f788cf8a89f589b2cff0", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6a267b87106a8b8681d0f5bc67a74ef3d586bad19905ab2c401c2b1abf92d5d1", "generation_seconds_batch": 21.14904306700919, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9430499076843262, "target_z": 1.0156249695517512, "ce": 6.268836498260498, "genuineness": 3.5188708305358887, "identity": 0.6525619029998779, "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_Fear/a8b465fd8e20e3cf1994b1af05227058872700352a24f788cf8a89f589b2cff0.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "46913bcfe683522ae8ac8d1e60560beed878a33ec0c350ada25a72af939a357e", "generation_seconds_batch": 15.321196867967956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05769777297973633, "target_z": -0.4316406120594942, "ce": 6.149696350097656, "genuineness": 4.457139015197754, "identity": 0.758721113204956, "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_Fear/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "a90e9263c3d68085419372568109bd7d4e1964a9215b5a1218bfcd1149a79603", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8af8e599519fd9c4ede578d26a45259ebe1b0cc89a92c221acc3aeedf7e332ab", "generation_seconds_batch": 22.282004495966248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4448153078556061, "target_z": 0.20117187271638134, "ce": 5.990842819213867, "genuineness": 4.6203155517578125, "identity": 0.2944457530975342, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a90e9263c3d68085419372568109bd7d4e1964a9215b5a1218bfcd1149a79603.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": "a9335ffbe3d5ef1fec227e0e5c3a5b81add6e9c51565f6ba5565c0776c686aed", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9b1f6b0d354ba3f66d71059a7e435ac6ad5ff689bbae2b87ced67cb52717a91d", "generation_seconds_batch": 15.68596842396073, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8451831340789795, "target_z": 4.125000146151595, "ce": 6.141753673553467, "genuineness": 3.998987913131714, "identity": 0.6765009164810181, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi, quand nous pourrons parler ?", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a9335ffbe3d5ef1fec227e0e5c3a5b81add6e9c51565f6ba5565c0776c686aed.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "4cdd425bdcbe4887d84a4be9e2fff0d804ea72984d1690600b299ec9bf8cc083", "generation_seconds_batch": 15.872273468994536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03977566957473755, "target_z": -0.46093747868622575, "ce": 6.23706579208374, "genuineness": 4.65797233581543, "identity": 0.780389666557312, "hypothesis": "Ton message est arrivé après mon départ, je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi, quand nous pourrons parler ?", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "a979560f8eaad7b93fbcd1dfa6caeefb02d6d27edb12f63ca8ff4b7940c69ace", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7bf0e09c47bc303c69f79fdb189f7f953ec62a81ee0f189a6ad04f38316d92c1", "generation_seconds_batch": 20.805961609934457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7255949974060059, "target_z": 0.6601562302086382, "ce": 5.637393951416016, "genuineness": 4.3881025314331055, "identity": 0.7153858542442322, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mann 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_Fear/a979560f8eaad7b93fbcd1dfa6caeefb02d6d27edb12f63ca8ff4b7940c69ace.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "a9a07e5c18a4bb08413b79c5b3306e56ee6d1bf183f5fd7ef089833176cc1d8b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2705a2db832df12f88e4f54b1079295c73a8e598d1a68a2ca48836872e4dec68", "generation_seconds_batch": 21.15058339596726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6981680393218994, "target_z": 2.2499999025656034, "ce": 6.2767791748046875, "genuineness": 4.419482707977295, "identity": 0.5931507349014282, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a9a07e5c18a4bb08413b79c5b3306e56ee6d1bf183f5fd7ef089833176cc1d8b.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "a9d3bdaa7176ae484051ef3010dc41beb7222b4ee0004987e94e6e9df2dea0be", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c3676619a05f8de8d3041a67cc9be8cda99261ab5a21807b73ed75cdc86d0078", "generation_seconds_batch": 22.40661163907498, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7841942310333252, "target_z": 2.3906250182689495, "ce": 6.2767791748046875, "genuineness": 4.105680465698242, "identity": 0.5566365122795105, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/a9d3bdaa7176ae484051ef3010dc41beb7222b4ee0004987e94e6e9df2dea0be.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": "aa17835dcb9c53142c5bf02207bdee72a50bb4bfb3201e77661cb44db0c7117b", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8b4e5fa8c36ebebfe9978e3527e5e75cb6b5fdd738314d2a0984dd405d46d559", "generation_seconds_batch": 15.401366346981376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17359407246112823, "target_z": -0.24218749086552532, "ce": 6.046441555023193, "genuineness": 4.162164688110352, "identity": 0.22635866701602936, "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_Fear/aa17835dcb9c53142c5bf02207bdee72a50bb4bfb3201e77661cb44db0c7117b.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "aa69671e7fbbb1ca7a1352ae73ec249adb5a8b05d114b6e680127f38ba3a83cc", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "151deca74fc535939860fcabbf73ec10be384f598a7fc948fad835b61219e947", "generation_seconds_batch": 15.500296029960737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6540138721466064, "target_z": 3.812499975641401, "ce": 5.903473377227783, "genuineness": 3.9801597595214844, "identity": 0.6293420195579529, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/aa69671e7fbbb1ca7a1352ae73ec249adb5a8b05d114b6e680127f38ba3a83cc.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "aa6b05e6d35ea3e0d9e307155f3b0f0c2df3ae648316ac6bec9551d3c1dd13da", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d7ab4f96ff7d1ba2cd6db4f2fcdc79cc25153fdb2fd3d24036386be730bff722", "generation_seconds_batch": 15.762852851999924, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8128695487976074, "target_z": 2.4374999269242026, "ce": 5.935244083404541, "genuineness": 4.042920112609863, "identity": 0.5231428146362305, "hypothesis": "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_Fear/aa6b05e6d35ea3e0d9e307155f3b0f0c2df3ae648316ac6bec9551d3c1dd13da.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "aa806e85c24b04a8be86a2b82a6c4472bf17a14c1f2672dafb3ab083ee6205a2", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ee062f35e96ae9b8500a8675881fa7b2dd0e252c85f7b9e4f29ec35dbd0b2f09", "generation_seconds_batch": 20.12596257298719, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023048341274261475, "target_z": -0.48828127283618666, "ce": 6.046441555023193, "genuineness": 4.457139015197754, "identity": 0.7545148730278015, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/aa806e85c24b04a8be86a2b82a6c4472bf17a14c1f2672dafb3ab083ee6205a2.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": "aaff7a14a95597cc69041ed53f3429d55cf5a7146a28959ab1c7951b42da432e", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c3c7f04d3d54745fe46f12e342b4bef95e8db7aba7458b528f9dabc1e6da4ae9", "generation_seconds_batch": 15.988870390923694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6922476291656494, "target_z": 3.874999853848405, "ce": 5.514282703399658, "genuineness": 3.7291181087493896, "identity": 0.594426691532135, "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_Fear/aaff7a14a95597cc69041ed53f3429d55cf5a7146a28959ab1c7951b42da432e.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": "ab1cfcbf6261fd0e18bf78553592d419613e9be9877eb7ad72c970b4bbd02722", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5c06f61b38581a84fc41ca0c1500b5b6dac31a297792545b287b16bad54c2e4d", "generation_seconds_batch": 16.428143683006056, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18972396850585938, "target_z": -0.2158203060297471, "ce": 6.284721851348877, "genuineness": 4.243753433227539, "identity": 0.4132692217826843, "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_Fear/ab1cfcbf6261fd0e18bf78553592d419613e9be9877eb7ad72c970b4bbd02722.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": "ab3cd975ce13ad45f7c461f1a3578904e9869222518b2820d64576d6e933da55", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6822024f1f10f6a5b7cfb5dbf54f39942106e2507e2e6e0d8417c151c146b235", "generation_seconds_batch": 16.52821892197244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2655942142009735, "target_z": -0.09179689098533067, "ce": 6.0305562019348145, "genuineness": 4.406930446624756, "identity": 0.5870499610900879, "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_Fear/ab3cd975ce13ad45f7c461f1a3578904e9869222518b2820d64576d6e933da55.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "d60e640b6d418ecb174579679c08eed53a6d02985b2414ec90d0c1826bad23db", "generation_seconds_batch": 17.05563118297141, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08995756506919861, "target_z": -0.3789062423879378, "ce": 6.467403411865234, "genuineness": 4.18099308013916, "identity": 0.42725276947021484, "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_Fear/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "aba19b73f9402b789412b2bfb710ea2d01d289c94654745fde581dd722c700a9", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d92383d76fd5a1fd9406739699d3e98582e1571afff4d6558a7dbc52650d3c22", "generation_seconds_batch": 20.450351436971687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5487635135650635, "target_z": 0.371093708894864, "ce": 6.165581703186035, "genuineness": 4.20609712600708, "identity": 0.4667940139770508, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/aba19b73f9402b789412b2bfb710ea2d01d289c94654745fde581dd722c700a9.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "ac57fd13d133b6fb10aa65ccbda772c87a58bb6a21818a6e812fb4b1a2f8ed54", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fc3f7e0fe0fbe9e349d3d028c7d348db4621233b13c14a352af704dd39c0cddd", "generation_seconds_batch": 22.427691484917887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03141200542449951, "target_z": -0.4746093757612062, "ce": 6.24500846862793, "genuineness": 4.256305694580078, "identity": 0.48566532135009766, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ac57fd13d133b6fb10aa65ccbda772c87a58bb6a21818a6e812fb4b1a2f8ed54.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": "acb9610a10856c4ba3e9f72907e5d67dfbed66d800c61d92348ff04f4297f2cf", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a56af61b6226e672cc1eca08839d6ea0ea224db4936a08f4b488ef1031023fda", "generation_seconds_batch": 17.80264463298954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3636220693588257, "target_z": 1.7031249939103503, "ce": 5.982900142669678, "genuineness": 3.6663577556610107, "identity": 0.24778251349925995, "hypothesis": "De sleutels liggen op de keukentafel. Ik kijk in de la... Daarna. Stit 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_Fear/acb9610a10856c4ba3e9f72907e5d67dfbed66d800c61d92348ff04f4297f2cf.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "acebacd2503068392be12001a4a5409690323f1b694c2c8c38e9387fec88e15f", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "211c8389c6c762e0d0421ec8af7436e534a947c0f989a0bd0bf08bf5c66121d2", "generation_seconds_batch": 20.126898562069982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3014920949935913, "target_z": 1.6015624969551752, "ce": 5.871703147888184, "genuineness": 3.8420867919921875, "identity": 0.421475350856781, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/acebacd2503068392be12001a4a5409690323f1b694c2c8c38e9387fec88e15f.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "ad67bd21585ebbcabffb28e808029c59addc18e1b92d36d27b26f169ecfe9e0c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c878601c0424bcd79f20ac85bcfd5679589f15b49139d5680fad55d79ff1c09c", "generation_seconds_batch": 16.272744219051674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8834168910980225, "target_z": 4.187500024358599, "ce": 5.367343425750732, "genuineness": 3.798154592514038, "identity": 0.6833506226539612, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ad67bd21585ebbcabffb28e808029c59addc18e1b92d36d27b26f169ecfe9e0c.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "ad69cb417d94e9793aa73f4e38406a21d37a8fdc1b845fa84b4837d90c9b111a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a1c066a21f97d6ebb7c8899f9678a204a25bbc01549c6acf6c1331df960d5379", "generation_seconds_batch": 21.160569493076764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9849218130111694, "target_z": 2.7187499634621015, "ce": 5.2918877601623535, "genuineness": 3.6789097785949707, "identity": 0.37891286611557007, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ad69cb417d94e9793aa73f4e38406a21d37a8fdc1b845fa84b4837d90c9b111a.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "adc784917a8295964acce5f7587ee2bac9b127df082b37732e08b3e67906dfef", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "635e85131bc11b0376da0c038d97ab04e372903d1ccddbbdf26244d316358384", "generation_seconds_batch": 22.393934487947263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7687153816223145, "target_z": 4.0, "ce": 5.863759994506836, "genuineness": 3.8546390533447266, "identity": 0.7387109994888306, "hypothesis": "Die Tür 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_Fear/adc784917a8295964acce5f7587ee2bac9b127df082b37732e08b3e67906dfef.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "f61839381785f85fa3b72d9e51f2eb03e7077f48b6746cc26fe626c6b717cf0e", "generation_seconds_batch": 15.144577005063184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05530816316604614, "target_z": -0.435546854447432, "ce": 6.197352409362793, "genuineness": 4.243753433227539, "identity": 0.6315922141075134, "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_Fear/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "add4dff179bf0f0494835efcd8edc456c745a6e696b6a65e83e5ed53cfcbf609", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "92adcd7a8b1d1e95656305fac2b2f3234c2a056693259860d6044a55dfcaec7c", "generation_seconds_batch": 15.437776311999187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.284872055053711, "target_z": 4.843749914744903, "ce": 5.855817794799805, "genuineness": 4.13078498840332, "identity": 0.6872292757034302, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/add4dff179bf0f0494835efcd8edc456c745a6e696b6a65e83e5ed53cfcbf609.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": "ade091073f54f86af2c8285f0b8084400d509090ae8935141c6556fde106bf4f", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1504287f16a9031cccc1ba89084d002e24c2c724b50bcef6b53664340b1b7919", "generation_seconds_batch": 16.270587361999787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.979001522064209, "target_z": 4.343750109613696, "ce": 6.0146708488464355, "genuineness": 3.9173994064331055, "identity": 0.5673359632492065, "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_Fear/ade091073f54f86af2c8285f0b8084400d509090ae8935141c6556fde106bf4f.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "adee8dfeae9d7037536e9833bf84620a964289659ed583ec83400a3d6bd358b5", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "52ca90f0d054e8b64ab92e1b082d7d426a9fde49309c053f360777b21b7317ac", "generation_seconds_batch": 20.608600694919005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5775461196899414, "target_z": 3.687499829489806, "ce": 5.538110733032227, "genuineness": 3.8044304847717285, "identity": 0.5299396514892578, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/adee8dfeae9d7037536e9833bf84620a964289659ed583ec83400a3d6bd358b5.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "ae2da02f267ed6d465403ddd8d4a73a5ca64d1fc9eed39ee2ec2edec48fe64db", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "474246521271537a426ed9a02ef335bcfb3a8a33913b3aa4ca50434cbcdeebad", "generation_seconds_batch": 16.47285230504349, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9000368714332581, "target_z": 0.9453125091344746, "ce": 6.046441555023193, "genuineness": 4.243753433227539, "identity": 0.5522239208221436, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. Esta, 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_Fear/ae2da02f267ed6d465403ddd8d4a73a5ca64d1fc9eed39ee2ec2edec48fe64db.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "21d95c33fcd7fe316a321b7c2392b806fc9df13e2c446a97e7067d570c89e1bd", "generation_seconds_batch": 15.893842538935132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0481393039226532, "target_z": -0.4472656303284436, "ce": 6.38003396987915, "genuineness": 3.9927117824554443, "identity": 0.42583173513412476, "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_Fear/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "ae4fdd1e509142cca5bdc961d306f4ffd869a6cfffe3c3f179d96d3dfc4fb63e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3214fad9631566aeea9fd3dff6ee055ebd8d5c9b3c4ec2357f96b18996530b1c", "generation_seconds_batch": 22.532724275020882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.290792465209961, "target_z": 3.2187499634621015, "ce": 6.0146708488464355, "genuineness": 3.948779582977295, "identity": 0.44724756479263306, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ae4fdd1e509142cca5bdc961d306f4ffd869a6cfffe3c3f179d96d3dfc4fb63e.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "ae5408b0bc2139e8b9864050d797e4aed54e7fd2d0d8d82c260df78de7519219", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "34a9b882004f56b652ea8fc9c5fdd00180def8c8e114589f010e63ecda84c528", "generation_seconds_batch": 21.938596609048545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1676737070083618, "target_z": 1.3828125334930739, "ce": 5.3792572021484375, "genuineness": 4.394378662109375, "identity": 0.7428447008132935, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ae5408b0bc2139e8b9864050d797e4aed54e7fd2d0d8d82c260df78de7519219.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "ae7e7c2205f6d03ccdec88ef262af3447a5d6e415272f0e9e76c8341b2d224af", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ff5443e14104fb4ba899b7f9a61fb0acb15300daef953c621d50de3637810de6", "generation_seconds_batch": 21.068553318968043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0720891952514648, "target_z": 1.2265626431067698, "ce": 6.0146708488464355, "genuineness": 4.3504462242126465, "identity": 0.786103367805481, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ae7e7c2205f6d03ccdec88ef262af3447a5d6e415272f0e9e76c8341b2d224af.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": "aed9681a3ca1b3ce42f5bfece13a055196ae292e7305af2631a8e74957d42b06", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fb202fb94525c7bd1115781ad9fa97e1967c42336759b72e98f7a9ae2a33909a", "generation_seconds_batch": 13.96907474391628, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8128695487976074, "target_z": 2.4374999269242026, "ce": 5.502368927001953, "genuineness": 3.6224255561828613, "identity": 0.5318443775177002, "hypothesis": "The k keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/aed9681a3ca1b3ce42f5bfece13a055196ae292e7305af2631a8e74957d42b06.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "af498fdbe83ff5ad4b6172cffd51cc774740e4913cc31d05b5075d695bd854b3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b75cdca2fa381a74780314da5fbf036c020f9551bc30d2fa11db370f0541aded", "generation_seconds_batch": 20.45713584299665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006321042776107788, "target_z": -0.5156250182689494, "ce": 6.24500846862793, "genuineness": 4.319066047668457, "identity": 0.60056471824646, "hypothesis": "I found th 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_Fear/af498fdbe83ff5ad4b6172cffd51cc774740e4913cc31d05b5075d695bd854b3.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "afa176195f4a1a5158346a3df1bbf42a29db1a9c7727563649a4bde82c39ff39", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d7f606da27c8b9c0833192ddea74d65b00cf84ad82acd7c829424a05ef5cf7e4", "generation_seconds_batch": 23.165738193085417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5917766094207764, "target_z": 0.4414062667465369, "ce": 6.157639026641846, "genuineness": 4.331617832183838, "identity": 0.399867981672287, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/afa176195f4a1a5158346a3df1bbf42a29db1a9c7727563649a4bde82c39ff39.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "afba6a0be20d2202d27e9f4915ca193509ad00f7df6868ce898081597ee779bc", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "914cc2f9d0f8597d62af45893cb851b701906a5e44ff93a8c741f33bedb01cb5", "generation_seconds_batch": 20.450351436971687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6062216758728027, "target_z": 3.7343751278826454, "ce": 6.181467056274414, "genuineness": 3.6789097785949707, "identity": 0.6528710722923279, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/afba6a0be20d2202d27e9f4915ca193509ad00f7df6868ce898081597ee779bc.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "afbde79c374c7e80ab0ee9f269f490b0ef5c8069a35a604483400e9ce8e3a19d", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "88dde9e88ec500cf8a71588cd0c54c8a40f2686fcbcc2074be48137cad5a1da4", "generation_seconds_batch": 15.593859028071165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2966592013835907, "target_z": -0.04101564250774311, "ce": 6.268836498260498, "genuineness": 4.494794845581055, "identity": 0.31553903222084045, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/afbde79c374c7e80ab0ee9f269f490b0ef5c8069a35a604483400e9ce8e3a19d.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": "afd8a9ecabf90847c4ecb37974453b4047720fb43adb323e101e33fc9d3c70d1", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "755134d37de6021e0d143544e8e08faddd38dc312e8765371d007269e8d3dd70", "generation_seconds_batch": 13.96907474391628, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0386345386505127, "target_z": 1.171875054806848, "ce": 6.141753673553467, "genuineness": 3.9927117824554443, "identity": 0.6482126116752625, "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_Fear/afd8a9ecabf90847c4ecb37974453b4047720fb43adb323e101e33fc9d3c70d1.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "b005e418f224f852d6fa7dc1eb9059819441f6ccdc602c6ef607e2416192d103", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6e6bc4e5d872ad83b0ce9c4bec24eb65e4e95751753f8e70be99f139f39491de", "generation_seconds_batch": 25.474248272017576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00562700629234314, "target_z": -0.5351562302086382, "ce": 6.022613525390625, "genuineness": 4.444586753845215, "identity": 0.7895813584327698, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b005e418f224f852d6fa7dc1eb9059819441f6ccdc602c6ef607e2416192d103.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "b038c571afe8772a9c47465b03851ea2a1402fae9a3e6f8429a611a1f6790e70", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b38f164a1ebfc53c4ce4e1092139e80250df80febd1decbbb23d5b602c21d220", "generation_seconds_batch": 24.813716487959027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0911523699760437, "target_z": -0.3769531211939689, "ce": 6.181467056274414, "genuineness": 4.406930446624756, "identity": 0.6068826913833618, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b038c571afe8772a9c47465b03851ea2a1402fae9a3e6f8429a611a1f6790e70.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "b0839d51e8b4c29511443b90327a496686395106b4888d05aa92af364afc6bee", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "67b667fb7936f4015e83975423bed0e3e85d8805f4fbdf0aff8ac6b2aa60e97e", "generation_seconds_batch": 17.849984709988348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6599342823028564, "target_z": 2.187500024358599, "ce": 5.796247482299805, "genuineness": 3.8295347690582275, "identity": 0.688248336315155, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b0839d51e8b4c29511443b90327a496686395106b4888d05aa92af364afc6bee.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "b087c23df4c0d4c923af8c0e86a9f1c9778ee62a7372ccce30bf662bfa541f16", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5f7592ec467ba921c1fb950ae4d820f436700b42e20fc6a1fbdb1af0aedb8f79", "generation_seconds_batch": 22.48658072494436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13894465565681458, "target_z": -0.2988281272836187, "ce": 6.24500846862793, "genuineness": 4.68307638168335, "identity": 0.6656910181045532, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b087c23df4c0d4c923af8c0e86a9f1c9778ee62a7372ccce30bf662bfa541f16.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "b10ec2ca4ce1af82a8ed1feec69c06ce61f006abd5ed21b8c4f5d00577117820", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8e1fc3e814b2509460730f895f8ce937160360034d008febff35b0e98d2104aa", "generation_seconds_batch": 22.559096329961903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5679876804351807, "target_z": 3.6718748599380553, "ce": 4.979145050048828, "genuineness": 3.5471129417419434, "identity": 0.4660477340221405, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre a 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_Fear/b10ec2ca4ce1af82a8ed1feec69c06ce61f006abd5ed21b8c4f5d00577117820.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "b11e8fac2785c18c64fcffe31536ffd3db2952f0c4a02e9ce54162e1cced53a2", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d08cee637dcc721e5d09c836190b909bb9745c2c04b32f980ab5d29472b55a29", "generation_seconds_batch": 23.16731479507871, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6886096000671387, "target_z": 2.2343749330138523, "ce": 5.661221981048584, "genuineness": 4.469690799713135, "identity": 0.6480631828308105, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b11e8fac2785c18c64fcffe31536ffd3db2952f0c4a02e9ce54162e1cced53a2.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "b12da6db5ce2df541fcb0b9df0f0a06097db29e768ca9e1a6237272afa357c3c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3b7367815f1d9495b75f82910389048b20c4187a0803638b080370cc47d08e34", "generation_seconds_batch": 20.00157908804249, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04455488920211792, "target_z": -0.4531249939103502, "ce": 6.1020402908325195, "genuineness": 4.268857479095459, "identity": 0.25206702947616577, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b12da6db5ce2df541fcb0b9df0f0a06097db29e768ca9e1a6237272afa357c3c.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "b14d1ff2bf45be0313fcf6e431e6aeee964273e7bf0ee742e0a626f069856d8b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fe3d6c5e3f0498fcda27eac749d72896772ab199504bff8d18772f077ad866b2", "generation_seconds_batch": 24.034196887048893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008016645908355713, "target_z": -0.5390625213137742, "ce": 6.300607204437256, "genuineness": 4.325342178344727, "identity": 0.6613589525222778, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b14d1ff2bf45be0313fcf6e431e6aeee964273e7bf0ee742e0a626f069856d8b.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": "b1c73262279d15191cf73cfda13219b08a872f8c7894c40acda582982181f4a7", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "04243cef1a035164a5da72ca1e83e82161bd09e4376d83c520d44f51dc8e9f36", "generation_seconds_batch": 15.167716562049463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3342209756374359, "target_z": 0.02038576031372317, "ce": 6.181467056274414, "genuineness": 4.18726921081543, "identity": 0.5992286801338196, "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_Fear/b1c73262279d15191cf73cfda13219b08a872f8c7894c40acda582982181f4a7.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "b1e109e590d867571b8b892e9c22c53a18de1589cae05787a11b785a94a80c1d", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f0c28d7dac35d7b73bee01d6a9954600e289e3f5c8666c90a12fd2ed93318181", "generation_seconds_batch": 20.391506297979504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1198813915252686, "target_z": 1.3046874908655253, "ce": 5.974957466125488, "genuineness": 4.168440818786621, "identity": 0.6475088000297546, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b1e109e590d867571b8b892e9c22c53a18de1589cae05787a11b785a94a80c1d.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "b2f36d55288b2b8e147b6c9d9512ae67bf4f0c4d11f989a5c7c8440c1b6800a6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2d20c7f9f7d5bbf0fbf9ff38e39e11139e6749eb7106373b6b43a086e9b520a2", "generation_seconds_batch": 20.986956006032415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02663278579711914, "target_z": -0.4824218605370818, "ce": 6.292664527893066, "genuineness": 4.570107460021973, "identity": 0.6446301341056824, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b2f36d55288b2b8e147b6c9d9512ae67bf4f0c4d11f989a5c7c8440c1b6800a6.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "b32a880a6cb4a8fa1245d5d733e4327ce41a1726d0ec8a465701c39a32166121", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7411b818524a906c586279fb23f110fb958fbba207c60a82a71660fb36ced947", "generation_seconds_batch": 21.874762470950373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.204766273498535, "target_z": 3.0781248477587555, "ce": 5.895530700683594, "genuineness": 3.7918784618377686, "identity": 0.6144247055053711, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b32a880a6cb4a8fa1245d5d733e4327ce41a1726d0ec8a465701c39a32166121.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "b40d7cddc04e389840ebd286d492be5fc4cd59735d89df0b640ecd66295dca07", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f762d67e63aa5b6c22c8582de744eff3b025aae1c1fd1e66287eebd5b60c189c", "generation_seconds_batch": 16.14694984909147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0039314329624176025, "target_z": -0.5195312606568872, "ce": 6.109982967376709, "genuineness": 4.6956281661987305, "identity": 0.6575708985328674, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b40d7cddc04e389840ebd286d492be5fc4cd59735d89df0b640ecd66295dca07.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "feb7208e641b09cae0f0679cabb31514b93ef5d660cb833528c5b84260431629", "generation_seconds_batch": 15.909556800033897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018269121646881104, "target_z": -0.4960937576120622, "ce": 6.2767791748046875, "genuineness": 4.419482707977295, "identity": 0.509896993637085, "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_Fear/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "b48062aff13c17eaf22d42ee2669edcd8b6b7934bdaa61afeacae32ef3f9ed5b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a6f986492ee82ee3e4ef952970db4b315ddcba7123369b4bfdf8cabc9873b16d", "generation_seconds_batch": 24.66057071101386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4669192433357239, "target_z": 0.2373046878806031, "ce": 6.070269584655762, "genuineness": 4.595211505889893, "identity": 0.6872261762619019, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b48062aff13c17eaf22d42ee2669edcd8b6b7934bdaa61afeacae32ef3f9ed5b.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "b4e87bdd657f95961fe0def3c270900f2016b96c8a1832a3ff8c5dfd7a558ebc", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a917a1e7b024317457803c979b3059e9171700de8d3e730188c177eee5180d67", "generation_seconds_batch": 25.820912210969254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11385370790958405, "target_z": -0.3398437454327627, "ce": 6.149696350097656, "genuineness": 4.268857479095459, "identity": 0.4128001928329468, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b4e87bdd657f95961fe0def3c270900f2016b96c8a1832a3ff8c5dfd7a558ebc.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "b598cbbc63fd1ca10053c77a63583e0f55a274004d089ff80dea13137c5446a1", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4ecfa4e90bfa94cff0c6052c6917d8cd2882a15f89daf722d88ef73330136d84", "generation_seconds_batch": 22.447419931995682, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3863770961761475, "target_z": 3.3750000487171983, "ce": 5.7406487464904785, "genuineness": 4.005263805389404, "identity": 0.4190426468849182, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b598cbbc63fd1ca10053c77a63583e0f55a274004d089ff80dea13137c5446a1.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": "b5b91640f47c791d8f2f7504ddcc6400f0d29645777fc45101585e60499d5ffe", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9cac34308f7e60e9b1f5c1a61f821831ad5996e6a54797b6211f77ccffce2399", "generation_seconds_batch": 20.690548429032788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.902533769607544, "target_z": 4.218749963462101, "ce": 4.685266494750977, "genuineness": 3.616149425506592, "identity": 0.5767530202865601, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter, bist du dem kleinen Neuestor? Ich warte auf der anderen Seite.", "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_Fear/b5b91640f47c791d8f2f7504ddcc6400f0d29645777fc45101585e60499d5ffe.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "b5f82c099890a69cf7350af81542279612f609c47a5c7af734700a032658c5e0", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e6e4b800542c010d4315522f50766fa983e552b989d42cf5dd123835d9e2371d", "generation_seconds_batch": 22.214332742034458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23273703455924988, "target_z": -0.14550779689527243, "ce": 6.09409761428833, "genuineness": 4.15588903427124, "identity": 0.4065266251564026, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b5f82c099890a69cf7350af81542279612f609c47a5c7af734700a032658c5e0.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "b653865ec4e8c7983accc7be5c31c25a027aef7080e5379890edd4a55a1608b0", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a2b36c85babfcf0073745793fb16c1c684f645380c5e507948831005e40fd678", "generation_seconds_batch": 15.851119911996648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6300104260444641, "target_z": 0.5039062423879378, "ce": 6.149696350097656, "genuineness": 4.243753433227539, "identity": 0.6483270525932312, "hypothesis": "I found the little box. It was beside a 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_Fear/b653865ec4e8c7983accc7be5c31c25a027aef7080e5379890edd4a55a1608b0.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "b6a7071838c8b164113ea33a5dc0daf28b79d2c23a0c81d108b23ff1aa55fd97", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "860fd09adb8e2ba6a8a8ac36bbfb348abc92abead3f9e814c78e3b76f7838ba7", "generation_seconds_batch": 22.925258026923984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8606618642807007, "target_z": 2.515624969551751, "ce": 5.514282703399658, "genuineness": 4.017816066741943, "identity": 0.2897568643093109, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b6a7071838c8b164113ea33a5dc0daf28b79d2c23a0c81d108b23ff1aa55fd97.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": "b710cf3e9f04d4ad1a3cbb9c8bb2f1ea78add7d70e29545028b75f52e9ce35c9", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a447d7e43d7ecaf90594fbcec073033d0306c86e061fbdae4d3a37fd95a1edd0", "generation_seconds_batch": 15.093045728979632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0529721975326538, "target_z": 1.1953125091344747, "ce": 6.268836498260498, "genuineness": 4.256305694580078, "identity": 0.6729607582092285, "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b710cf3e9f04d4ad1a3cbb9c8bb2f1ea78add7d70e29545028b75f52e9ce35c9.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": "b72d482cbc3349cf22878cd3c49e1994a1c1e85e5337565243c9116ea13aa0fb", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d078c0750cd5f8a3c49ce9039efc85ceeeaa4831894f574d6c0647b3b543d625", "generation_seconds_batch": 16.654042379930615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03619122505187988, "target_z": -0.46679689098533067, "ce": 6.1020402908325195, "genuineness": 4.381826400756836, "identity": 0.45761018991470337, "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_Fear/b72d482cbc3349cf22878cd3c49e1994a1c1e85e5337565243c9116ea13aa0fb.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "b7fa8f48a9c0125a66a0de73b0167fce6d88c0d910e801e8e4cf2687605e3003", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6b7d896ca7cb56940bf4bb5851206b53b224d072e118b9c120663807f3a3ff1e", "generation_seconds_batch": 20.580970279988833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4628448486328125, "target_z": 3.500000194868793, "ce": 5.879645347595215, "genuineness": 3.6412534713745117, "identity": 0.5059269666671753, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b7fa8f48a9c0125a66a0de73b0167fce6d88c0d910e801e8e4cf2687605e3003.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "b81a588a6af5651492fb66912e303b27e9b72f9005c2a2948940e5906489e866", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5f5b0299e57e42354e81b4b304e32c8284b6900431c7baf8583c46000517ad7e", "generation_seconds_batch": 25.715901441057213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9275710582733154, "target_z": 2.6249999512828017, "ce": 5.597680568695068, "genuineness": 3.9048471450805664, "identity": 0.6780518889427185, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Ça t'en vend pour lui, tu aurais peur. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.8333333333333334, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b81a588a6af5651492fb66912e303b27e9b72f9005c2a2948940e5906489e866.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "b8b08a9bb9ec099f267a3270333de1b1006d49d22a8ef158291d9bbce81a90b5", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "36333433fce639ed244454f26c676729f07e640d652c960d9905e519bd383995", "generation_seconds_batch": 14.448327674064785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.056502968072891235, "target_z": -0.4335937332534631, "ce": 6.229123115539551, "genuineness": 4.055472373962402, "identity": 0.4578109681606293, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b8b08a9bb9ec099f267a3270333de1b1006d49d22a8ef158291d9bbce81a90b5.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "b9299d5c1403ae5c74e83b8d237965994f933f0fa4aef9963315b391930e0b33", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7c5fa346d2b46948a58cf6535af93c5facf89ae1c5a93068a4c258aaac260e3e", "generation_seconds_batch": 22.86590414494276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9598846435546875, "target_z": 4.3125001705101935, "ce": 5.657250881195068, "genuineness": 3.9048471450805664, "identity": 0.5521372556686401, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b9299d5c1403ae5c74e83b8d237965994f933f0fa4aef9963315b391930e0b33.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "b94efde8a345f375c858717e92570de8eaef3f6902913206ecd544e981ffa9d4", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e86fdfb28d759cb30ce8bb04adc112b3112ae5bbe8eb6376fadb707b610cffa2", "generation_seconds_batch": 27.507756265928037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08159391582012177, "target_z": -0.3925781151043191, "ce": 5.816103935241699, "genuineness": 4.080576419830322, "identity": 0.5172830820083618, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/b94efde8a345f375c858717e92570de8eaef3f6902913206ecd544e981ffa9d4.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "b99b9996fec5c65e345dba522e393b22ab061b4a31ee6527cfa777b3646e5cbd", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "10f8dfb340040284715753f06acd844e29b95cb508418bd134233e949d9037d1", "generation_seconds_batch": 16.45315010007471, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6694927215576172, "target_z": 2.2031249939103503, "ce": 6.070269584655762, "genuineness": 4.15588903427124, "identity": 0.6757768988609314, "hypothesis": "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_Fear/b99b9996fec5c65e345dba522e393b22ab061b4a31ee6527cfa777b3646e5cbd.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "ba3e9bb1fe34af77fae0e04439e6a78c9a4a859e75969e72c829cdc00aaf669b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5e827851f27d5535c3db30f6bfebf9096cbe5cc9fda5df9ca30a3c0d0bf32f8e", "generation_seconds_batch": 16.731221021036617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8379068970680237, "target_z": 0.8437500121792996, "ce": 6.24500846862793, "genuineness": 4.080576419830322, "identity": 0.533057689666748, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ba3e9bb1fe34af77fae0e04439e6a78c9a4a859e75969e72c829cdc00aaf669b.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "6bf661583ef8114aa6f36ffd3f494941f4324ad5206d166ad7443cabbe64d138", "generation_seconds_batch": 16.116828263970092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006321042776107788, "target_z": -0.5156250182689494, "ce": 6.038498878479004, "genuineness": 4.582659721374512, "identity": 0.702093780040741, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le ciroir, puis près de la fenêtre. Prends les quand tu partiras.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "bab867a58605afc80917c362b2897a8bf8ea763d81ee37ab01f775b9428759f5", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "387cbb2f7366aabc0902e0b8ae767612b9135278b3b6ca0a2a1c8321571bf0c4", "generation_seconds_batch": 20.09012075001374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.099623203277588, "target_z": 2.9062497929519076, "ce": 5.117149353027344, "genuineness": 3.7416701316833496, "identity": 0.658203125, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.3888888888888889, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/bab867a58605afc80917c362b2897a8bf8ea763d81ee37ab01f775b9428759f5.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": "bb14ebaa855aa59a14aec844af212895f4289356ec7520f09a79cea2071be835", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "18a15619366b66c400054e46450fe4827e5a4efba2ad0fcc22d670f76d8d729a", "generation_seconds_batch": 16.0854093269445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07800948619842529, "target_z": -0.3984375030448249, "ce": 6.197352409362793, "genuineness": 4.042920112609863, "identity": 0.7027899026870728, "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_Fear/bb14ebaa855aa59a14aec844af212895f4289356ec7520f09a79cea2071be835.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": "bb5766e0ce840b9a5f57060931b9b40e34653965adc024942c7a71345e770076", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4ab74b067889128217dba36f40e7f0b6ac8b6125ee8dfe4978631927142a2987", "generation_seconds_batch": 15.105036486056633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.329026222229004, "target_z": 3.281249841669106, "ce": 6.0146708488464355, "genuineness": 3.835810661315918, "identity": 0.15103916823863983, "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_Fear/bb5766e0ce840b9a5f57060931b9b40e34653965adc024942c7a71345e770076.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "bb7cf686dad1da52b3b59ef2e00599cd8f93f01d1295df7f3d7b978fd01a4722", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3038f46abfb1677f97f7e1a01c120abc595bcbfbba4f1b98721b95fc7c8ab301", "generation_seconds_batch": 15.694013391970657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6706339120864868, "target_z": 0.5703125578516729, "ce": 5.756534099578857, "genuineness": 4.482243061065674, "identity": 0.6529604196548462, "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_Fear/bb7cf686dad1da52b3b59ef2e00599cd8f93f01d1295df7f3d7b978fd01a4722.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "bbb86c567a91e042156c2559c5ee1aee51b6ec7e6fd0e937a0cb027caf8f2d6c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2834a8968a8e704095640ac5d75a52f69c136638e7ac6bfe77500ea586b3d989", "generation_seconds_batch": 23.154282761039212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1103229522705078, "target_z": 1.2890625213137743, "ce": 5.045665264129639, "genuineness": 3.760498285293579, "identity": 0.42679929733276367, "hypothesis": "Die Tür 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_Fear/bbb86c567a91e042156c2559c5ee1aee51b6ec7e6fd0e937a0cb027caf8f2d6c.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "bbc71ad4dc8504c429829f9ba51f7b281fdfdd5bae838ca78a0c54c4b073cd1e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9c5d96a5db1920b479f9cdced1657b5cf7bed21ab183560ba6097530d3435f2b", "generation_seconds_batch": 22.603372605051845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.056502968072891235, "target_z": -0.4335937332534631, "ce": 6.133810997009277, "genuineness": 4.482243061065674, "identity": 0.5196616649627686, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/bbc71ad4dc8504c429829f9ba51f7b281fdfdd5bae838ca78a0c54c4b073cd1e.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "bbda38765d5b487645c0e70c8c80fecb2b4fe9db0c9eeb0916eebf4781171de2", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "aaa810f84338beccbfecf6121e117138f826368e6cc5b62da62d6ebe16a31d47", "generation_seconds_batch": 21.691769947996363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.896613359451294, "target_z": 5.843749914744903, "ce": 5.816103935241699, "genuineness": 3.3745219707489014, "identity": 0.43460071086883545, "hypothesis": "The door is still open. I put your coat on the chair. Kill 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_Fear/bbda38765d5b487645c0e70c8c80fecb2b4fe9db0c9eeb0916eebf4781171de2.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "bcce7cbe3323ac1835cfb445adfb1579d2c7b86db484c2acd596eeb7662c5650", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0f1c97b6251ee7b27e634353e1c77eecb7c1987a30eb07e13357040da0e82bf1", "generation_seconds_batch": 23.47531853802502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42211395502090454, "target_z": 0.164062472596576, "ce": 5.454712867736816, "genuineness": 4.356721878051758, "identity": 0.7359215021133423, "hypothesis": "Die Tür. Die ist noch offen. Ich hab dein Mantel auf den Stuhl gelegt. 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_Fear/bcce7cbe3323ac1835cfb445adfb1579d2c7b86db484c2acd596eeb7662c5650.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "bce27364a8302331070b22b93017b1fde8a2ae909150888b9c7ea8c2d1e8e865", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9625c94cfc96965b9bbde87448cdcf98c1765d0685a056d1c7deb06a04de0520", "generation_seconds_batch": 20.95479655591771, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09832121431827545, "target_z": -0.3652343696715564, "ce": 6.117925643920898, "genuineness": 4.482243061065674, "identity": 0.5440911054611206, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/bce27364a8302331070b22b93017b1fde8a2ae909150888b9c7ea8c2d1e8e865.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "bd0a5d9b80c0373f5d1572f955f38435606f7866f5224bfd387ae19c9cf3fbfc", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a176b9c0a3c82c420235bee061ce312a4b8bd1114fe6bc41a1a751d671e55bd5", "generation_seconds_batch": 15.267978359013796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11146408319473267, "target_z": -0.34375001217929957, "ce": 6.260893821716309, "genuineness": 4.20609712600708, "identity": 0.330024391412735, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/bd0a5d9b80c0373f5d1572f955f38435606f7866f5224bfd387ae19c9cf3fbfc.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": "bd133b0cf08314991e0ccbd4bbd5592bce1017dac4c61a866e3f76141f96ec68", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "23f71b30ad89ed0b771e5b2d57ae10bbd0bf543261cdf247ea68488a8de01abf", "generation_seconds_batch": 16.520975314080715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26200979948043823, "target_z": -0.09765625456723734, "ce": 6.117925643920898, "genuineness": 4.3881025314331055, "identity": 0.18639212846755981, "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_Fear/bd133b0cf08314991e0ccbd4bbd5592bce1017dac4c61a866e3f76141f96ec68.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "bd2e7ec9dbb0b0604bed58d69986a948ce3d92bd3d125206c4ed88a225937c90", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "da2fd0d04f4163861df21ba10a9eea816160cc5a6b70a414ebdf300b7f5dd30f", "generation_seconds_batch": 22.962561806081794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.826066017150879, "target_z": 4.093749817310506, "ce": 5.665193557739258, "genuineness": 3.8797430992126465, "identity": 0.7869158983230591, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt de ranger que quand tu dis-moi quand tu es prêt !", "wer": 0.6111111111111112, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/bd2e7ec9dbb0b0604bed58d69986a948ce3d92bd3d125206c4ed88a225937c90.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": "be076a1378fc840233db8b853925eedafadc20600ebd1ec45cb7f20f8cfe1203", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "853bc99b86e82fb174d1ffd94b02673aac435d5d686dc4eaa5b516fb63af7826", "generation_seconds_batch": 22.055939739919268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.061389446258545, "target_z": 2.8437499147449032, "ce": 5.804190158843994, "genuineness": 3.8169827461242676, "identity": 0.7189507484436035, "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_Fear/be076a1378fc840233db8b853925eedafadc20600ebd1ec45cb7f20f8cfe1203.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "be0e5de17489672d42f952ada90bd24b7ad648aa22054d08a8d2e40aeafaca95", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "783929344b2ac44b8653025269c2aac263c830bbc98bdc3b25c1ce0681f52a24", "generation_seconds_batch": 20.601083906018175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0900650024414062, "target_z": 2.890625213137742, "ce": 5.3792572021484375, "genuineness": 3.672633647918701, "identity": 0.639991044998169, "hypothesis": "Die Tür 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_Fear/be0e5de17489672d42f952ada90bd24b7ad648aa22054d08a8d2e40aeafaca95.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "befd3a1a2a1a4e998f9c77f537950f30ff31e39a2249e0fbb37eefafbb421f5d", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6ee49608b8ca1146334280ba8c9f92939ab2fa820f3d7b5c873ec7109c82bf26", "generation_seconds_batch": 16.221557909972034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7542703747749329, "target_z": 0.707031236298288, "ce": 6.41180419921875, "genuineness": 4.118232727050781, "identity": 0.5721137523651123, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/befd3a1a2a1a4e998f9c77f537950f30ff31e39a2249e0fbb37eefafbb421f5d.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "bf0ca6d14277c8c82df2541860a607f6716f1761e07a7348f542fe10390a8755", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "be2c8b5a984e332072588d9beda98a9f3561f063a599cac38bc3525be4fd33fb", "generation_seconds_batch": 21.395532452967018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01996469497680664, "target_z": -0.5585937332534631, "ce": 6.165581703186035, "genuineness": 3.9299514293670654, "identity": 0.16536280512809753, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/bf0ca6d14277c8c82df2541860a607f6716f1761e07a7348f542fe10390a8755.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "bf45ac2c4c2729e3a858e0949185aae69863facdbddfffc7a9dfd42df1d4cfa7", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6bf9ae0b35ddbb011a1c63d1c3e473636ce7b860e6749899c1a5d33535cc571b", "generation_seconds_batch": 21.085711285937577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09354197978973389, "target_z": -0.3730468788060311, "ce": 6.23706579208374, "genuineness": 4.833701133728027, "identity": 0.6863634586334229, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/bf45ac2c4c2729e3a858e0949185aae69863facdbddfffc7a9dfd42df1d4cfa7.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "bf8e5044d0b8b0814f84ae699bab0adc2771f4b7d46829b470afd6990b4acd21", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "749c5c1201731073b815ee12c2a9b6c406cebc176074e549e32bd98a254f2440", "generation_seconds_batch": 20.36970352497883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0923471748828888, "target_z": -0.375, "ce": 6.070269584655762, "genuineness": 4.507347106933594, "identity": 0.4981454908847809, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/bf8e5044d0b8b0814f84ae699bab0adc2771f4b7d46829b470afd6990b4acd21.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": "bf9b643a05795f17f97d59da274cc8892926fa29e82a5ecc11106393061ea66d", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0433c44164a0bb77fe4ebd61e71a398be3053e5c02043c53510ef94be3e773b9", "generation_seconds_batch": 15.81298807298299, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1342191696166992, "target_z": 1.328125140061945, "ce": 6.078212261199951, "genuineness": 4.231201171875, "identity": 0.44858986139297485, "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_Fear/bf9b643a05795f17f97d59da274cc8892926fa29e82a5ecc11106393061ea66d.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "bfcfbb091f8be067d7fdd0b01e4361c1a87beb40cd957dc089172f03f803568b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6efc2aad66dcee4b95802b7f967955053f7c396abf75ce3f4f63d7b2c9130ae3", "generation_seconds_batch": 15.726269257022068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10071082413196564, "target_z": -0.3613281272836187, "ce": 6.046441555023193, "genuineness": 4.3504462242126465, "identity": 0.7346986532211304, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/bfcfbb091f8be067d7fdd0b01e4361c1a87beb40cd957dc089172f03f803568b.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "bfed4b503ce299e3922b4ef6cd2b0d6b34228ae7abe5b86419fd77344a7a9a71", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7efd488e4a76a385172a3f22b5b9c246d822a08035372ca8f75829ba7d627057", "generation_seconds_batch": 15.946229357970878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03977566957473755, "target_z": -0.46093747868622575, "ce": 6.133810997009277, "genuineness": 4.595211505889893, "identity": 0.7322385907173157, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/bfed4b503ce299e3922b4ef6cd2b0d6b34228ae7abe5b86419fd77344a7a9a71.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "c003574b931a82207371933f1debd6d2d9fbf92539421ce19c1195f0c3798390", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "19b5839617e6b42bb2101784e8ea20b541457a5ddc51cb0d445e1b14d1574555", "generation_seconds_batch": 25.820912210969254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12460696697235107, "target_z": -0.3222656303284436, "ce": 5.816103935241699, "genuineness": 4.325342178344727, "identity": 0.5027565956115723, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c003574b931a82207371933f1debd6d2d9fbf92539421ce19c1195f0c3798390.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "c0115c5bdafd5b48765fb4d84fc76237cd254ef74c9458290c3663db2062fbef", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "978fb2a6af11a4f5d23fb1f0791a5a107446937f444e3ecc3ddae1fba4fc455c", "generation_seconds_batch": 21.02299760002643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6515169739723206, "target_z": 0.5390625213137742, "ce": 5.855817794799805, "genuineness": 4.344170093536377, "identity": 0.5785799026489258, "hypothesis": "J'ai trouvé la 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_Fear/c0115c5bdafd5b48765fb4d84fc76237cd254ef74c9458290c3663db2062fbef.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "c0e017f8bc8492a3c408d56a969c2ca0976f3da071ba59a9d07d47682c12ba22", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fefbdc334319b81d03f5bb2d84e4f5a887f481420acef458b50776a739ea3528", "generation_seconds_batch": 23.37935300404206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5511531829833984, "target_z": 0.3750000487171982, "ce": 5.911416053771973, "genuineness": 4.519899368286133, "identity": 0.6039908528327942, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c0e017f8bc8492a3c408d56a969c2ca0976f3da071ba59a9d07d47682c12ba22.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "c141e4d8c4d43da4e6954dda871f728debba8f86d3679dd1d16c9ca4b4628ed1", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "93e9776ea33e5b9571ca81b8e560a198a4da41578bf43a66b93f672a589d1674", "generation_seconds_batch": 15.104398743947968, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12580177187919617, "target_z": -0.3203125091344747, "ce": 6.149696350097656, "genuineness": 4.607763767242432, "identity": 0.5888967514038086, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c141e4d8c4d43da4e6954dda871f728debba8f86d3679dd1d16c9ca4b4628ed1.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "c144289a209ddad074f73921998fb356adf76f2ac4b626ca53beb4e87ddf21ca", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c38426076056bfdaeb9547f41b88147b339b3dd259264e671467000b636b7ce2", "generation_seconds_batch": 22.04899805295281, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01518547534942627, "target_z": -0.5507812484775876, "ce": 6.3641486167907715, "genuineness": 4.425758361816406, "identity": 0.6513199210166931, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c144289a209ddad074f73921998fb356adf76f2ac4b626ca53beb4e87ddf21ca.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "c1d229fa6ad389e0300ebfc4f05cb9925780cc117a452f210dfbc87fccd82573", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "912f539191a816395ef1e92f63faab1428161329225adfbbe376cc5840002093", "generation_seconds_batch": 21.441346952924505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3982178270816803, "target_z": 0.125, "ce": 6.117925643920898, "genuineness": 4.7081804275512695, "identity": 0.5088602900505066, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c1d229fa6ad389e0300ebfc4f05cb9925780cc117a452f210dfbc87fccd82573.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "c20872ef27599056d61d81bb94b8f90ee009d26e9fdabfdf2dc002c8c31bef6c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "95dac49c97a77888d7dd8e887b4778b9c156d3d19957b42bd61b3fe4a638a0e2", "generation_seconds_batch": 22.474073264049366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09473678469657898, "target_z": -0.3710937576120622, "ce": 5.982900142669678, "genuineness": 4.494794845581055, "identity": 0.4077604413032532, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c20872ef27599056d61d81bb94b8f90ee009d26e9fdabfdf2dc002c8c31bef6c.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": "c2162003f6d1f82600b6e1328a5cba618e3e51f9e8dfb1323fddce57bb0623bf", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "53540fa47a0615ebde6cdbb8296da88a1d7e5122c3454a9b9fd31b0b5434a650", "generation_seconds_batch": 16.654042379930615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06367179751396179, "target_z": -0.4218750060896498, "ce": 6.229123115539551, "genuineness": 4.319066047668457, "identity": 0.36022043228149414, "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_Fear/c2162003f6d1f82600b6e1328a5cba618e3e51f9e8dfb1323fddce57bb0623bf.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "c231902434f4a03e94e86e38621a022628b6911d613baeabb8811c9abaa61639", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "dd23de4a381d79e129002ad0618a9c6517d7566f81767380df74dbe85313e7f5", "generation_seconds_batch": 20.938076326972805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.85110342502594, "target_z": 2.5, "ce": 5.855817794799805, "genuineness": 3.948779582977295, "identity": 0.6071242094039917, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c231902434f4a03e94e86e38621a022628b6911d613baeabb8811c9abaa61639.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "c2450ad4344da90c51e875e0854ce1e267527eb853819a13f6dd964960a7ed28", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "74c20024fa3026cf018db2bb4bf9edc6f634357a91c2535da693e438c1d42fe5", "generation_seconds_batch": 15.818316248012707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07084065675735474, "target_z": -0.41015623020863823, "ce": 6.213237762451172, "genuineness": 4.457139015197754, "identity": 0.703683078289032, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c2450ad4344da90c51e875e0854ce1e267527eb853819a13f6dd964960a7ed28.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "c24b2bce9b70236bf59fbd56a859e65d35ea8eec3c0e3732af16e4e1f401c3a9", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c04c1dcea62f7e645cc9b28078d560d22eebea288f151a09805e226c373a2431", "generation_seconds_batch": 20.56469000002835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4878283739089966, "target_z": 0.271484381850856, "ce": 6.086154937744141, "genuineness": 4.369274139404297, "identity": 0.6390429735183716, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c24b2bce9b70236bf59fbd56a859e65d35ea8eec3c0e3732af16e4e1f401c3a9.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": "c25854a8b170a401a321f39de54bd149402b2d47be019dbde3b2bb38e5630d66", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce3b5ad524302da68845eef91bc1712208d0c4c9cb38998255e6c2636e10ba9c", "generation_seconds_batch": 16.547512382967398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05172371864318848, "target_z": -0.4414062667465369, "ce": 5.959072113037109, "genuineness": 4.18099308013916, "identity": 0.445528507232666, "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_Fear/c25854a8b170a401a321f39de54bd149402b2d47be019dbde3b2bb38e5630d66.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "c318bcec779ffee6cc38c58a00530c81f91b4dc16f29e1b1e40ce80f1909cf50", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c3a47ad863ae7950c34b3f147a3d9b0fa93e9bd603ce41dd1e74203b274e2f38", "generation_seconds_batch": 21.52749768598005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05530816316604614, "target_z": -0.435546854447432, "ce": 6.0146708488464355, "genuineness": 4.796044826507568, "identity": 0.7314172983169556, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c318bcec779ffee6cc38c58a00530c81f91b4dc16f29e1b1e40ce80f1909cf50.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "c358e53134efc86c2fd10c135469e311c53a1ad3f112e2248338bdb18291c933", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "884398647a93ea93be0de68a874da9fb1469f5caf233a15a9e5b6a38e5ea8ade", "generation_seconds_batch": 21.93709330202546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07442507147789001, "target_z": -0.40429686662673153, "ce": 6.205295085906982, "genuineness": 4.494794845581055, "identity": 0.36335545778274536, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c358e53134efc86c2fd10c135469e311c53a1ad3f112e2248338bdb18291c933.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "a526cc51b22092b0d2ef2d9782e3f97e0fdf10a0cb08965362084e3f1de8e0f7", "generation_seconds_batch": 13.259259195998311, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0338016152381897, "target_z": -0.47070313337326847, "ce": 6.157639026641846, "genuineness": 4.519899368286133, "identity": 0.6522964239120483, "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_Fear/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "c3ea24903307788851ed6bbf820cc13c04fff73ea683704228c8dfc4b5df15ea", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "dca833dabb0b680d323796936ee5460e2122e20144fdea4db169823c33bab265", "generation_seconds_batch": 16.603821930941194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07800948619842529, "target_z": -0.3984375030448249, "ce": 6.213237762451172, "genuineness": 4.394378662109375, "identity": 0.7288941740989685, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c3ea24903307788851ed6bbf820cc13c04fff73ea683704228c8dfc4b5df15ea.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "c4351307ad5cd92f038afaf3948673f02576ecbc33982d55cf6ac6288e22c505", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0d4f02a1a4a1c47f8ba74f5b63d893a6097090d07e563c72253c189e5e6e0053", "generation_seconds_batch": 21.63867566292174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.434169292449951, "target_z": 3.4531248964759538, "ce": 5.514282703399658, "genuineness": 3.515732765197754, "identity": 0.09486190974712372, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude graam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c4351307ad5cd92f038afaf3948673f02576ecbc33982d55cf6ac6288e22c505.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": "c45250d049d29dc0a797352fabf76bea04c8ec4eda2106ce6d8d44ed072ce0b9", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3a176421dfda87eea5ba83e949420894d0adc87781af70264e90e08714ac4c7c", "generation_seconds_batch": 15.05554748501163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9334914684295654, "target_z": 1.0, "ce": 6.125868320465088, "genuineness": 3.911123275756836, "identity": 0.4932098090648651, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c45250d049d29dc0a797352fabf76bea04c8ec4eda2106ce6d8d44ed072ce0b9.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "c46a143f5453e3414b3e0bafd61646927f6447c4650c439b18f9eb6416d1c41c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "49ddc44aaa370e1697a0c9d266f42326e9ca4d8dfd42503d9417f3c2f3f2e999", "generation_seconds_batch": 22.041995184961706, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.13899827003479, "target_z": 1.3359374299690276, "ce": 5.974957466125488, "genuineness": 4.068024158477783, "identity": 0.3485749363899231, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar. Wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c46a143f5453e3414b3e0bafd61646927f6447c4650c439b18f9eb6416d1c41c.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "c63c4b78db87b90b0d78ca3a3b543f208d583648c931750cb15457bbdc4524d4", "generation_seconds_batch": 15.610990668996237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06725621223449707, "target_z": -0.4160156425077431, "ce": 6.221180438995361, "genuineness": 4.362998008728027, "identity": 0.4198741614818573, "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_Fear/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "c494299e948c58945bd6436bd8daf542ee08a2dec4697bbdc8cd926180a2c274", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d0ac183f9dff27e4fcbe501a8bc1fd07b7b67e71d6b07f4269a39d5940c2e3f5", "generation_seconds_batch": 20.452486629015766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05411332845687866, "target_z": -0.43750002435859914, "ce": 5.879645347595215, "genuineness": 4.507347106933594, "identity": 0.48152703046798706, "hypothesis": "He encontrado la cajita. Estaba junto a la. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.23529411764705882, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c494299e948c58945bd6436bd8daf542ee08a2dec4697bbdc8cd926180a2c274.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "c499093ff3b736911911c79fb5ab5b67ba799f6e5ae62d695641e0090ca91641", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3d96f4c5213b70e3d57ff5415d665368ccd6aea57113f822cf7a2391f36842c6", "generation_seconds_batch": 20.123499057022855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49499720335006714, "target_z": 0.28320310901466933, "ce": 5.982900142669678, "genuineness": 4.218649387359619, "identity": 0.3967406749725342, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c499093ff3b736911911c79fb5ab5b67ba799f6e5ae62d695641e0090ca91641.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "c4f19fda001d9a78b85709b22b11a78715fe98afe348b3a0ea16289a114d83b7", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "37075b7ad0228ea57af063fc650acf58a6af16ca885df5c140ae6c60ed05601f", "generation_seconds_batch": 16.214119294076227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05291852355003357, "target_z": -0.439453145552568, "ce": 6.062326908111572, "genuineness": 4.7332844734191895, "identity": 0.4675610065460205, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c4f19fda001d9a78b85709b22b11a78715fe98afe348b3a0ea16289a114d83b7.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "c4f82b8db431c23aba5049b218a0d2f2b5122cbee1c8c17d472693325090718c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "289e903a476d7a727668f47ce4f94bc7310e7051466e7dca8b977ce3d847361d", "generation_seconds_batch": 20.82196119299624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8606618642807007, "target_z": 2.515624969551751, "ce": 5.80021858215332, "genuineness": 3.7542223930358887, "identity": 0.4743657410144806, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c4f82b8db431c23aba5049b218a0d2f2b5122cbee1c8c17d472693325090718c.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "c534015265fb1871a079ffb121516cae7b575468b6e7b9c977697596617ccd36", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4346c9133fac378f3003428a0aa848c8712232c91a1b4fc9a16690d3eb78a9c5", "generation_seconds_batch": 19.677496960037388, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3875181674957275, "target_z": 1.742187417789728, "ce": 5.847874641418457, "genuineness": 4.105680465698242, "identity": 0.6633889675140381, "hypothesis": "Ik heb... ik heb het kleine 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_Fear/c534015265fb1871a079ffb121516cae7b575468b6e7b9c977697596617ccd36.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": "c554fe9ebff43b54ce0c4e92bc2a6f62723232b95b3dd3ff738b7a8596d43efd", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4ac1f693e943e4d4d167001da0128c3b85210daea8f0fe8ca33652ac0dc3e6e5", "generation_seconds_batch": 16.15732797398232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6025835275650024, "target_z": 2.0937500121792993, "ce": 5.772419452667236, "genuineness": 3.9801597595214844, "identity": 0.6106358766555786, "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_Fear/c554fe9ebff43b54ce0c4e92bc2a6f62723232b95b3dd3ff738b7a8596d43efd.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "c558756e5fba9e28e2a248d7da7ff9c47d77aa1132444f8bdaf98570f027bb10", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "cbf6e9f88ced6e7a887766ea91a0f754874159b9d4eb6fa2af38e06b3ffc0255", "generation_seconds_batch": 21.234881995012984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2775959968566895, "target_z": 1.5625000730757974, "ce": 5.526196479797363, "genuineness": 4.406930446624756, "identity": 0.6891725659370422, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c558756e5fba9e28e2a248d7da7ff9c47d77aa1132444f8bdaf98570f027bb10.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "c6187a36b1435518a3a3df89f3cd98ce2e33f291dc6158aca1491a8170f85a15", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c5bd93f77d21c67c0ae28ecb33deebcd558d122b348859f26b146495aab65c33", "generation_seconds_batch": 15.970283002010547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26410073041915894, "target_z": -0.09423825593989311, "ce": 6.09409761428833, "genuineness": 4.632867813110352, "identity": 0.35120418667793274, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c6187a36b1435518a3a3df89f3cd98ce2e33f291dc6158aca1491a8170f85a15.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "c62796c108d469e7dcee2d8330239e1ed906ef0aa6ac91521cbf18c3d0f49794", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "76853c5ccb4ba6152bcbf1c75e3b31c7a341c82415c83e5958224de2da319598", "generation_seconds_batch": 20.659014888107777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.017235279083252, "target_z": 4.406249987820701, "ce": 5.9431867599487305, "genuineness": 3.785602569580078, "identity": 0.4894126355648041, "hypothesis": "The 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_Fear/c62796c108d469e7dcee2d8330239e1ed906ef0aa6ac91521cbf18c3d0f49794.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "c674cd7787e390dafa3bd8a9ab337bae073175ee2cd00456893b385e68955652", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b73f8850c9d5b72bb525903297b7ec5a14887233887ae0bc2ed66e2b7867e1f4", "generation_seconds_batch": 20.36970352497883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029022395610809326, "target_z": -0.478515618149144, "ce": 6.205295085906982, "genuineness": 4.595211505889893, "identity": 0.5778542757034302, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c674cd7787e390dafa3bd8a9ab337bae073175ee2cd00456893b385e68955652.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "c689c1b13b33cf99fd0339008fdd36b6cc4f5619579d94849a5afe74485d6ce5", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e17b7cdb1cc845ddd97612ef8cbd30cde0e0a7b9fb1819997d8af243299f3658", "generation_seconds_batch": 23.52484746207483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6945300102233887, "target_z": 0.6093749817310506, "ce": 5.8875885009765625, "genuineness": 4.13078498840332, "identity": 0.5957170724868774, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c689c1b13b33cf99fd0339008fdd36b6cc4f5619579d94849a5afe74485d6ce5.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "c8142a734355eddf551cdcef5b11c473a56606600f1fbbc057870bedf28f3236", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1b941ab55624384c7c79fd6c988247e8b86e39a0e8d6371d270aaf9dee52baeb", "generation_seconds_batch": 21.197157065034844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.204766273498535, "target_z": 3.0781248477587555, "ce": 5.752562999725342, "genuineness": 3.7793264389038086, "identity": 0.5078374147415161, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos. ¿O qué 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_Fear/c8142a734355eddf551cdcef5b11c473a56606600f1fbbc057870bedf28f3236.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "0be90cb48c5d70ae4b2c82418866580b113cdc21a4f8d58521c5a770aee58592", "generation_seconds_batch": 15.144577005063184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.056502968072891235, "target_z": -0.4335937332534631, "ce": 6.1020402908325195, "genuineness": 4.3881025314331055, "identity": 0.6521481275558472, "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_Fear/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "c83cbd77cb2ccfb1a553601ad82418cca2877ed5251312adb7ef2318d9cf6143", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "22d568b5093cb83f72581ed7ea40bd8faf7c17470298a5d03cbc0d990cff5991", "generation_seconds_batch": 22.698083093971945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7591569423675537, "target_z": 3.984375030448249, "ce": 5.998785495758057, "genuineness": 3.6412534713745117, "identity": 0.5632338523864746, "hypothesis": "I found the little box. It was beside the old Wingot. Wing 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_Fear/c83cbd77cb2ccfb1a553601ad82418cca2877ed5251312adb7ef2318d9cf6143.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "2aac33dea615ac98a803f3b7d2fbc14a4423dea5fb37ad63c13eaab46602f772", "generation_seconds_batch": 16.598602466052398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011100292205810547, "target_z": -0.5078124847758756, "ce": 6.308549880981445, "genuineness": 4.2751336097717285, "identity": 0.456221342086792, "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_Fear/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "c8c45451250149923fa395d7e0503404e02eb8119ffa76ab474776ba10647ec8", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e29f348410319c2a1807f1cf52a10d98afab4da7f443256c5d3cc9429b48c732", "generation_seconds_batch": 19.324236282031052, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24886691570281982, "target_z": -0.11914063641809333, "ce": 5.720792293548584, "genuineness": 4.281409740447998, "identity": 0.592998743057251, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c8c45451250149923fa395d7e0503404e02eb8119ffa76ab474776ba10647ec8.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "c8c636bd98ebf8bb0be645a66960b6345c46e12dbf0005152b95d5dc9232c373", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d143b277748284d7d14c33b4303a07e60946c7ae4354d5a341c0cf0f0bf95043", "generation_seconds_batch": 20.04254691605456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 4.164250373840332, "target_z": 6.281250231406691, "ce": 5.990842819213867, "genuineness": 3.418454170227051, "identity": 0.4952295124530792, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c8c636bd98ebf8bb0be645a66960b6345c46e12dbf0005152b95d5dc9232c373.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "c8e0fb21ef3ae20663f46578a849d551d21a8e7bf012b4da30c93359dbda7846", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "809a0ca12534fadd5ad084d73e7eff3b902e8c83ddb867ad0f23ed117a493efd", "generation_seconds_batch": 23.002459125011228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006321042776107788, "target_z": -0.5156250182689494, "ce": 6.054384231567383, "genuineness": 4.331617832183838, "identity": 0.7572585940361023, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c8e0fb21ef3ae20663f46578a849d551d21a8e7bf012b4da30c93359dbda7846.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "c94e2b7e3a1fe959ddb407ffe35675397785aa994954215c97f6c48310ee6303", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4190691dda9e9aa5913a55188f0f51e57d0aa63a5223d2550090483d2308ada0", "generation_seconds_batch": 21.810549877933227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.55250883102417, "target_z": 5.281249841669106, "ce": 5.1926045417785645, "genuineness": 3.6914620399475098, "identity": 0.6975764036178589, "hypothesis": "J'ai trouvé. j'ai trouvé la petite boîte. Elle était prête. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.2631578947368421, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c94e2b7e3a1fe959ddb407ffe35675397785aa994954215c97f6c48310ee6303.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": "c9833469de740067f4d78d8db19e9b043535d7390703f77a8f818357aa19526d", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6da1ba0dce8580c71f832cd8555c2712a8cbfa33e9aaf50226b3f516ffc03f3e", "generation_seconds_batch": 20.509978918009438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0327141284942627, "target_z": 2.7968750060896497, "ce": 5.148920059204102, "genuineness": 3.773050308227539, "identity": 0.40282732248306274, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, les le bien, et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c9833469de740067f4d78d8db19e9b043535d7390703f77a8f818357aa19526d.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "c9b3bb2a0fedf45d4da12fb6a91d4290958b787c5dc6c2ac845a565576fcd6f6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "42b3c7217a305f46cedd24f70fecc0af8cd69fd2be532d744eb722060bd52c13", "generation_seconds_batch": 15.054047149955295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08398352563381195, "target_z": -0.3886718727163813, "ce": 6.1020402908325195, "genuineness": 4.369274139404297, "identity": 0.7630351781845093, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/c9b3bb2a0fedf45d4da12fb6a91d4290958b787c5dc6c2ac845a565576fcd6f6.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": "c9f75b97bfffabb4d159a46c391810af3199e498936adc278a448930d52b647c", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a32da205f47a557bb2b3eaef8814f031425a3c4bc09fbb7eb8d4bb015045299c", "generation_seconds_batch": 16.681625318014994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7841942310333252, "target_z": 2.3906250182689495, "ce": 5.895530700683594, "genuineness": 4.055472373962402, "identity": 0.7035201191902161, "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_Fear/c9f75b97bfffabb4d159a46c391810af3199e498936adc278a448930d52b647c.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "ca1220e2ef35ea2053f8f72b951fd22b73132621a0cf222ad1e39ecac617ec9c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "177b89994e46e2476676509868f1dc11d9f3ce59aacb480a5d2e153f7b1500f5", "generation_seconds_batch": 20.50147660204675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1485031098127365, "target_z": -0.28320313337326847, "ce": 6.181467056274414, "genuineness": 4.218649387359619, "identity": 0.6526576280593872, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ca1220e2ef35ea2053f8f72b951fd22b73132621a0cf222ad1e39ecac617ec9c.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "ca4d77911e6ccff110301d4c609ecd9bcf5d8b6a214add33603470f7aa675fe3", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e5462da3413b957baba4a1b8ebb81f1e1d716ad2a9c29c6ff4679e23f26715e2", "generation_seconds_batch": 16.603821930941194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04455488920211792, "target_z": -0.4531249939103502, "ce": 6.1894097328186035, "genuineness": 4.444586753845215, "identity": 0.7176312804222107, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ca4d77911e6ccff110301d4c609ecd9bcf5d8b6a214add33603470f7aa675fe3.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "caab4dc07c9a44287bfa767a63fda7ac45e5428acd282097954c12c58045bf9e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8fdb69852994a0765c5f42646b9bb62349cfe29b332afdeb9872db837f96296d", "generation_seconds_batch": 22.872313371044584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7829457521438599, "target_z": 0.7539062423879378, "ce": 5.839932441711426, "genuineness": 4.419482707977295, "identity": 0.5805916786193848, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/caab4dc07c9a44287bfa767a63fda7ac45e5428acd282097954c12c58045bf9e.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "cb5a369257e57a2d1aff8d8b37bc574be00453fd078eec788ed698180e0e0626", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e1ed1e6334cf029d87b823b0e4826f06f815ebf0f0d5c2d22090b4c15f4a42df", "generation_seconds_batch": 20.949759008944966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0923471748828888, "target_z": -0.375, "ce": 6.1020402908325195, "genuineness": 4.250029563903809, "identity": 0.6629348397254944, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/cb5a369257e57a2d1aff8d8b37bc574be00453fd078eec788ed698180e0e0626.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "cc1d97ba4e25f59f13a4d1e8194a24ee4dc740bb5cfbf461b5bb85a4eac72158", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e6eae1cff6d4ec790a5f9f648af59c2c6857f812385a1b9cb1b14ead8801d470", "generation_seconds_batch": 14.49848424398806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07084065675735474, "target_z": -0.41015623020863823, "ce": 6.181467056274414, "genuineness": 4.595211505889893, "identity": 0.5527838468551636, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/cc1d97ba4e25f59f13a4d1e8194a24ee4dc740bb5cfbf461b5bb85a4eac72158.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "cc377cfcf428dc18ff2dcd743a5c1b58d5115f5e8323d48c18104dc9f8d3fc73", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e4a8b45793d7b4edeada1405f8bbe194ed45094d807e569c36867069f879247f", "generation_seconds_batch": 20.714859631028958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.022354304790496826, "target_z": -0.5624999756414009, "ce": 6.284721851348877, "genuineness": 4.582659721374512, "identity": 0.6210840344429016, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/cc377cfcf428dc18ff2dcd743a5c1b58d5115f5e8323d48c18104dc9f8d3fc73.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "cc86320224a4daaab7abd4db9e13f2fd4580676b351f1a504acc0cce401c037a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "270d51d3581176fd0526515cbc1f7b4ddeb4def0e710b9b344d0a68bd8593cdb", "generation_seconds_batch": 22.80758644803427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013489902019500732, "target_z": -0.5039062423879378, "ce": 6.308549880981445, "genuineness": 4.7081804275512695, "identity": 0.41189125180244446, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/cc86320224a4daaab7abd4db9e13f2fd4580676b351f1a504acc0cce401c037a.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "cd4cb2fd5f9b3811c1aaf7e285ff37e4b5b39d4c45ba5fa974a1af224236f899", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "690376727fdc74d3604bb513b794666a57c3f1a8d2c22943136ecd8f0c11b282", "generation_seconds_batch": 22.95254271000158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5213366746902466, "target_z": 1.9609375761206222, "ce": 5.959072113037109, "genuineness": 4.3504462242126465, "identity": 0.35323184728622437, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/cd4cb2fd5f9b3811c1aaf7e285ff37e4b5b39d4c45ba5fa974a1af224236f899.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "cd95a50acc09d77d29a7d179670a169286c4bb6dba6a6b718ed8dd04ec6a12b0", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "43ce9dedf532451c3ee643dd4310ee146bc6acffd9c77bec5525a40b5585766b", "generation_seconds_batch": 16.654756297008134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.029076099395752, "target_z": 1.156250085255097, "ce": 6.165581703186035, "genuineness": 4.319066047668457, "identity": 0.5132561922073364, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/cd95a50acc09d77d29a7d179670a169286c4bb6dba6a6b718ed8dd04ec6a12b0.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "ce04637cf4680ef3ff98bbf16fb149300281eb703c6f6d4d7674010aad7638df", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f2f71e2450de306d3293104de9916ab2b66e40ac45ba3fa1dd1cd5f3f61a7231", "generation_seconds_batch": 21.30846319696866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006321042776107788, "target_z": -0.5156250182689494, "ce": 6.300607204437256, "genuineness": 4.381826400756836, "identity": 0.48509857058525085, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ce04637cf4680ef3ff98bbf16fb149300281eb703c6f6d4d7674010aad7638df.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "ce051f6a1c9641852f0506c7ada100a78285445194d6379f399ed980938246f4", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d5957b9163084ed4d915153a267c86ad93ff2576d48cfb2e84c50f2a60c69db6", "generation_seconds_batch": 16.45315010007471, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9216506481170654, "target_z": 4.2499999025656034, "ce": 5.728734970092773, "genuineness": 3.735394239425659, "identity": 0.6522592306137085, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ce051f6a1c9641852f0506c7ada100a78285445194d6379f399ed980938246f4.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "ce169d014441dffe0c5510150bc37434d9c1198307cc4610a2963c64a0be5c66", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4ed779e173fe05e37c04a8ade5566f6bb357c6175bda5b88a5039cc00acc54aa", "generation_seconds_batch": 20.74579138099216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008016645908355713, "target_z": -0.5390625213137742, "ce": 6.340320587158203, "genuineness": 4.15588903427124, "identity": 0.5269707441329956, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster, wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ce169d014441dffe0c5510150bc37434d9c1198307cc4610a2963c64a0be5c66.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "ce893fbae73b99cc775ee883e26bff8b338d182a81e444c51a23031988e8144f", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "adf3542c6a207f03864eecca2ae4bf8bd4d680d73b82fc583771114b47e7bac5", "generation_seconds_batch": 22.254719292046502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11624331772327423, "target_z": -0.3359375030448249, "ce": 6.23706579208374, "genuineness": 4.532451152801514, "identity": 0.702440083026886, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ce893fbae73b99cc775ee883e26bff8b338d182a81e444c51a23031988e8144f.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "cebbacd782985f3e7ce27feea297a8adbd3cbbf26ebaf2c916a56d55121e932c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "bca41314667e6cc985426be5cff108939c57e8e60a4431e3436d48ecbd520e49", "generation_seconds_batch": 15.776296164025553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.13785719871521, "target_z": 2.9687500608964976, "ce": 5.6334228515625, "genuineness": 4.2374773025512695, "identity": 0.816806972026825, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/cebbacd782985f3e7ce27feea297a8adbd3cbbf26ebaf2c916a56d55121e932c.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "cecfe2028ce2d088e40e3a591f1f12557620dbc6dd1cad4d7728ff80cc69d934", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0ad88e55dde0322d7031320cdb35f6dc41db5e7dff253622a3fb639007711c37", "generation_seconds_batch": 22.14964445598889, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3827389478683472, "target_z": 1.7343749330138525, "ce": 5.609594821929932, "genuineness": 4.256305694580078, "identity": 0.5959617495536804, "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_Fear/cecfe2028ce2d088e40e3a591f1f12557620dbc6dd1cad4d7728ff80cc69d934.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "ced622ec723706b71fe1360364ff449e19b5b4d91d6827c43d55f7bcdcc4bb01", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "598d42798c49b84f11150331f24abe2b4c15a5995fba3d7bef1c656ecf5c5244", "generation_seconds_batch": 20.26379417197313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0481929779052734, "target_z": 1.1875000243585991, "ce": 5.959072113037109, "genuineness": 4.243753433227539, "identity": 0.4261380434036255, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ced622ec723706b71fe1360364ff449e19b5b4d91d6827c43d55f7bcdcc4bb01.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "87ab946f8967201fcf575bf5b0b73691b712ae6d135d241f86a0404c724df45a", "generation_seconds_batch": 16.677892565028742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06964585185050964, "target_z": -0.4121093514026071, "ce": 6.38797664642334, "genuineness": 4.7458367347717285, "identity": 0.6073321104049683, "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_Fear/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "cfd65bbd58c1f651c83e0b96e646862b89fe226ff3fd352331858cfb01bd8e76", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "49104d0f6eb00eeb8252e15320c100af2d8892121549a87ffed121bf76635fd3", "generation_seconds_batch": 23.52484746207483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7757769227027893, "target_z": 0.7421875152241244, "ce": 5.542081832885742, "genuineness": 4.419482707977295, "identity": 0.5157063603401184, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/cfd65bbd58c1f651c83e0b96e646862b89fe226ff3fd352331858cfb01bd8e76.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "d05ce0b74e4457f4943946f651dc7bd28a120490f078d327adcf348d74cf16e5", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "1d49c0575fe2cfaa23df2a37b97933f6103ab910f5b09ad418ac4be1bc6ee636", "generation_seconds_batch": 22.069165130960755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2716755867004395, "target_z": 3.187500024358599, "ce": 5.7684478759765625, "genuineness": 3.7040140628814697, "identity": 0.4169292747974396, "hypothesis": "He encontrado la camista. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/d05ce0b74e4457f4943946f651dc7bd28a120490f078d327adcf348d74cf16e5.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "d09ddeb7a4872b417ebcdc2409f48f10833bbdab6dd92b6c1e0b8d4364f59621", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e9b3fd80f3133a619b468cd9951f074549c2e9ab0929e8999d4968b71297a644", "generation_seconds_batch": 21.018805671017617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6694927215576172, "target_z": 2.2031249939103503, "ce": 5.728734970092773, "genuineness": 4.099404335021973, "identity": 0.6966292858123779, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/d09ddeb7a4872b417ebcdc2409f48f10833bbdab6dd92b6c1e0b8d4364f59621.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d254c1e96e8af39ae7326a98b546504f0df2bc80eacdd157fe4bac0a01676054", "generation_seconds_batch": 14.752619983046316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.060087382793426514, "target_z": -0.4277343696715564, "ce": 6.356205940246582, "genuineness": 4.287685871124268, "identity": 0.4249410033226013, "hypothesis": "I wrote the number on the envelope, read it carefully, and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.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": "d132b88625bc99cec4d8a5f0af2030c10de305a932f11ea448498870256664bf", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "82a9f870c3727e8323da44844698275f185d45932c79d4f0a71d77411a471521", "generation_seconds_batch": 21.896005881018937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.965804934501648, "target_z": 2.687500024358599, "ce": 5.601652145385742, "genuineness": 3.402764081954956, "identity": 0.03460903465747833, "hypothesis": "Te weg gaat linksaf, naar de brug. Loop verder. Tot aan het kleine Houten Hek. Ik wacht aan de andere kant.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/d132b88625bc99cec4d8a5f0af2030c10de305a932f11ea448498870256664bf.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "d14a72571f7cc3b038279ba86148f1237e280fd587d9ce3aecee566def12e0b6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "30f6c591bb33097f2a4836275ff4e0c80444979830d7c5614279ae239e7bff05", "generation_seconds_batch": 19.871444149990566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2921786904335022, "target_z": -0.04833983480582689, "ce": 5.788304805755615, "genuineness": 4.243753433227539, "identity": 0.46295636892318726, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/d14a72571f7cc3b038279ba86148f1237e280fd587d9ce3aecee566def12e0b6.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": "d1bd35e4b0c01a801708ef9a7724d60bb2a0bd8629d792c382d7edbdca3e172b", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4421b33c655b3a76cc6ab51194320f4d2f99c9456be484138b04bb189fbf21ce", "generation_seconds_batch": 16.475885153049603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9275710582733154, "target_z": 2.6249999512828017, "ce": 6.213237762451172, "genuineness": 4.074300289154053, "identity": 0.5458967685699463, "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_Fear/d1bd35e4b0c01a801708ef9a7724d60bb2a0bd8629d792c382d7edbdca3e172b.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "d1e35e6af69eb2fe5b9b7def10e3930e55b3675dd7df1449d0f16cea8bfa05dd", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "24aa2391ea64f8406d0a0f5c1f9487b192fedcab6ecba6e690b7d38642f1b544", "generation_seconds_batch": 22.39672655495815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.787832260131836, "target_z": 4.031249939103502, "ce": 5.315715789794922, "genuineness": 3.6789097785949707, "identity": 0.5226575136184692, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alken 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_Fear/d1e35e6af69eb2fe5b9b7def10e3930e55b3675dd7df1449d0f16cea8bfa05dd.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "d201e54dbdd48d70b7eff355f5f97978ba85bbdf64538c1be31e577fda221e64", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1de26b71d8c67fe50f22898aea7ae9f8788ead3658480d915a6c62c29c28fcbe", "generation_seconds_batch": 21.099755798000842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.024296760559082, "target_z": 1.1484374056104285, "ce": 6.173524379730225, "genuineness": 4.168440818786621, "identity": 0.3531000316143036, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/d201e54dbdd48d70b7eff355f5f97978ba85bbdf64538c1be31e577fda221e64.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "506bc8549454530a68bad017d66092a3ac8e21a5848923b3aaccc3aa6e0b795f", "generation_seconds_batch": 13.421577680972405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03141200542449951, "target_z": -0.4746093757612062, "ce": 6.221180438995361, "genuineness": 4.494794845581055, "identity": 0.640820324420929, "hypothesis": "Las llaves están en la mesa de. en la mesa de la cocina. Miré en el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.17391304347826086, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "d2901d3c70c2507a0768596a3928d0b092308ec3b072f10206809ed3c280e26a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "577a4a370525fefd085c6672d118d0d9c7c623dbf7da10cf759fbcf00091a6f9", "generation_seconds_batch": 21.426383660989814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0147383213043213, "target_z": 1.1328124360586773, "ce": 5.784333229064941, "genuineness": 4.457139015197754, "identity": 0.6512220501899719, "hypothesis": "La porte 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_Fear/d2901d3c70c2507a0768596a3928d0b092308ec3b072f10206809ed3c280e26a.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "d2db5a0e3bb9342585b5ba2e2cefe83033474b2f6f1928fb9e6883db893635fa", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7f1989a888e984bae32cb48255942acf09306e3c5423df0c2dc243749aab71db", "generation_seconds_batch": 20.197385517065413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47826990485191345, "target_z": 0.25585936358190664, "ce": 6.221180438995361, "genuineness": 4.15588903427124, "identity": 0.4268420338630676, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/d2db5a0e3bb9342585b5ba2e2cefe83033474b2f6f1928fb9e6883db893635fa.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": "d3cc979d84e61a891cd63ad424b8f15a094429aebd7e92d39760fcd564b68ae2", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "acf52af52b52696c7c4df48a4a986bcdbaa2e7eea5ed02ad6d5face5384a74d1", "generation_seconds_batch": 21.34954846499022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6922476291656494, "target_z": 3.874999853848405, "ce": 5.748591423034668, "genuineness": 3.7291181087493896, "identity": 0.5294795632362366, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/d3cc979d84e61a891cd63ad424b8f15a094429aebd7e92d39760fcd564b68ae2.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": "d3d49f330dc5fdf6de291825cb8e4a655fdba2ce9e83027ba73f5602cb8b2c65", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b60c94da928b5a0f09fc9f26d006264732af4218eec1540529e8c4259efc3673", "generation_seconds_batch": 15.105036486056633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.625338554382324, "target_z": 3.7656250669861477, "ce": 5.831989288330078, "genuineness": 3.7918784618377686, "identity": 0.22291094064712524, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik laste het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/d3d49f330dc5fdf6de291825cb8e4a655fdba2ce9e83027ba73f5602cb8b2c65.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "e1954f3e4b3258c5aff092a2ca645d9121f2ae8d5886097cdb68c0cfa6bf28bf", "generation_seconds_batch": 14.290664704982191, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.061282187700271606, "target_z": -0.4257812484775876, "ce": 6.157639026641846, "genuineness": 4.557555198669434, "identity": 0.40457770228385925, "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_Fear/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "d457f0c9b4cd5304f564776b8ae2fc93af081018fdace0479e9bc48b6c56a5e3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fa80bd8a407058f6e398b618fb2f8b2aaef7e95fdc4dc6fb0ede44cbd3ed1b19", "generation_seconds_batch": 16.585426885052584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04336008429527283, "target_z": -0.4550781151043191, "ce": 6.086154937744141, "genuineness": 4.6956281661987305, "identity": 0.5672463178634644, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/d457f0c9b4cd5304f564776b8ae2fc93af081018fdace0479e9bc48b6c56a5e3.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "d4af4bf8fcc5023e794daaafc9606571f396d9703464c88682307b682d607b4b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9c717541cbb6e19f2000b9b9d3cef2e1855e8cac3ca08bf0436a173867ab4f5a", "generation_seconds_batch": 23.016964314039797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1485567092895508, "target_z": 1.3515623995207786, "ce": 5.744620323181152, "genuineness": 4.406930446624756, "identity": 0.7118973731994629, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/d4af4bf8fcc5023e794daaafc9606571f396d9703464c88682307b682d607b4b.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "d58ebfadec6c04109271ba98b2530e52a5591f07e16c62f3b0f79fb25d0f4c12", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a0459c065e48445a08fbb89ba60e58d853906a0a8a6a1a1ccefab1a9b3a0150f", "generation_seconds_batch": 16.106028825975955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05411332845687866, "target_z": -0.43750002435859914, "ce": 6.109982967376709, "genuineness": 4.7834930419921875, "identity": 0.745485246181488, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/d58ebfadec6c04109271ba98b2530e52a5591f07e16c62f3b0f79fb25d0f4c12.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "d5dad7a844c017e545fc66c5a1f7440b33052dff431cabe0e6095eb890754322", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "bd39c5c9b2444b191b151d723f43352fc3f807c231bfcb76f089f7f41f4ddc8d", "generation_seconds_batch": 20.74579138099216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13058100640773773, "target_z": -0.3125, "ce": 6.324435234069824, "genuineness": 4.68307638168335, "identity": 0.4441820979118347, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/d5dad7a844c017e545fc66c5a1f7440b33052dff431cabe0e6095eb890754322.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "d668cb558223d19d858a8a9929dddb662dbc5b06bd0034674422ae09334dd817", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce1b26a3d6bc9cd0d9061c9f998d71b04c3d7f5cf07806d98f639ada2ba9a7ad", "generation_seconds_batch": 21.873020619968884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07561987638473511, "target_z": -0.4023437454327627, "ce": 6.109982967376709, "genuineness": 4.381826400756836, "identity": 0.39590758085250854, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/d668cb558223d19d858a8a9929dddb662dbc5b06bd0034674422ae09334dd817.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "d7dbb166d90e7a9b1b6ebac933ac2afde9150561241191ebf469ae387636487e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6522f9de5cab346026a772d760696df44b4086ea297f98b0054870efbef8f56c", "generation_seconds_batch": 16.058046050020494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9669460654258728, "target_z": 1.0546874908655253, "ce": 6.046441555023193, "genuineness": 4.356721878051758, "identity": 0.5977857112884521, "hypothesis": "J'ai trouvé la petite boîte, elle était. elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/d7dbb166d90e7a9b1b6ebac933ac2afde9150561241191ebf469ae387636487e.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "d7ea6d2c5a28c5d07d7ba4cd8344e971f170eaac51590a6cf16db6a7ef75c433", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c34e47314c67fb89571a65118d0d71e38eaa70b4a2a0e82155d2a6fdd8930b59", "generation_seconds_batch": 21.314802272012457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7208157777786255, "target_z": 0.6523437454327626, "ce": 6.062326908111572, "genuineness": 4.218649387359619, "identity": 0.3987603783607483, "hypothesis": "Die Tür ist noch offen. Ich hab. ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist, das I was on Sayu.", "wer": 0.42105263157894735, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/d7ea6d2c5a28c5d07d7ba4cd8344e971f170eaac51590a6cf16db6a7ef75c433.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "d824a297996a2558afbc6abcb72912ff21772c4b2481db8555f8f41e15f66680", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "88df7a7f6b8ee4a9666d20eaca4ed515dba69c017c7f81609200cad419e40bec", "generation_seconds_batch": 22.474073264049366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1210225522518158, "target_z": -0.3281249939103502, "ce": 6.205295085906982, "genuineness": 4.231201171875, "identity": 0.503917932510376, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, want van her je klaar bent.", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/d824a297996a2558afbc6abcb72912ff21772c4b2481db8555f8f41e15f66680.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "d89c6c4f208c0364265e9c8dbe9ade33c63116880fdcd5b1019fe73ad890a314", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "711de6b37fe06e06d900b6e0129bbfd9c70d4aba20bb94f4178c0375257f41af", "generation_seconds_batch": 15.425279182032682, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015879511833190918, "target_z": -0.5, "ce": 6.173524379730225, "genuineness": 4.720732688903809, "identity": 0.7127589583396912, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/d89c6c4f208c0364265e9c8dbe9ade33c63116880fdcd5b1019fe73ad890a314.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": "d8e457c9c098e4b5d9ecb70d0e23447936accaa39273efe80cdc0e08593029ad", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ec56aafd851875cae262208fe93c030a5158437ede3e938b5863599f7d8a8bea", "generation_seconds_batch": 23.521791590959765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.634896993637085, "target_z": 3.7812500365378985, "ce": 5.752562999725342, "genuineness": 3.5345609188079834, "identity": 0.5737351775169373, "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_Fear/d8e457c9c098e4b5d9ecb70d0e23447936accaa39273efe80cdc0e08593029ad.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "da4fdaf9ba357f63827c3f025c055a8965f5a26516ff104e1591b7f4959f6985", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9deea844e2e97938b2e101d451e388fde40a3904f36cb964c2f498c6c42eb7fc", "generation_seconds_batch": 22.140452536055818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2213863581418991, "target_z": -0.1640624969551751, "ce": 6.038498878479004, "genuineness": 4.231201171875, "identity": 0.48018142580986023, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen aan 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_Fear/da4fdaf9ba357f63827c3f025c055a8965f5a26516ff104e1591b7f4959f6985.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "da9d53b027e9566e5cab98ca299ff133007dae0fafcfeee9cb3305329cb510d2", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2dc5463c308ec2cf622c1d309beae1cd567d71253963295c5a9d23049c60e112", "generation_seconds_batch": 17.296131321112625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7279846668243408, "target_z": 0.6640625700309725, "ce": 6.038498878479004, "genuineness": 4.061748504638672, "identity": 0.49989593029022217, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude... het oude raam. We kunnen samen 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_Fear/da9d53b027e9566e5cab98ca299ff133007dae0fafcfeee9cb3305329cb510d2.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "dabfa8576c535b7a9b055832376cdbb041922f85bd56061455a4666aa7c53a0e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9797b13456f6b09a851901e1a54cae52e2f49706b2b5a3c8caa913aebd010a2a", "generation_seconds_batch": 16.164207125082612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12341216206550598, "target_z": -0.3242187515224124, "ce": 5.673136234283447, "genuineness": 4.519899368286133, "identity": 0.6647980213165283, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/dabfa8576c535b7a9b055832376cdbb041922f85bd56061455a4666aa7c53a0e.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "dae4a00d9d2db5f24eb950f85a59f0c9eaacdcd43cdf438d5cc8ec1852d9619c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c84ee03ee571f1bbd3f5107c221752e64e9ec3133fde901931243eaead85690f", "generation_seconds_batch": 21.314802272012457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6849715709686279, "target_z": 0.5937500121792996, "ce": 5.4388275146484375, "genuineness": 4.381826400756836, "identity": 0.43624868988990784, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/dae4a00d9d2db5f24eb950f85a59f0c9eaacdcd43cdf438d5cc8ec1852d9619c.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "d66b426c91d2d89daacb3ba41bf4149c6bef52280a6ce84a5ffaaa3a8bf29c1e", "generation_seconds_batch": 17.05563118297141, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08756794035434723, "target_z": -0.3828125091344747, "ce": 6.4912309646606445, "genuineness": 4.319066047668457, "identity": 0.3787927031517029, "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_Fear/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "db3b12df8817c3e6c5b6b732952483074ab81c37bce6baa2098ad0e6b65cd946", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fa43472464ab9767cde875f73e9db097d887a9e9b207367d8f9e8a16c333c92d", "generation_seconds_batch": 24.20421591901686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9753633737564087, "target_z": 2.7031249939103503, "ce": 5.839932441711426, "genuineness": 3.5596652030944824, "identity": 0.6410223841667175, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/db3b12df8817c3e6c5b6b732952483074ab81c37bce6baa2098ad0e6b65cd946.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": "db3cf77313b69d49e8bd1d775eb4e47da148025ce31b2bf05eda3ce281ce69d3", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1f0fb8e3725618564f9873d019f6cb4fdd8e4f4b4023d3ecab11dc0eb833e256", "generation_seconds_batch": 15.750365309068002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7423223257064819, "target_z": 0.6875000243585991, "ce": 5.760505676269531, "genuineness": 4.080576419830322, "identity": 0.5680549144744873, "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_Fear/db3cf77313b69d49e8bd1d775eb4e47da148025ce31b2bf05eda3ce281ce69d3.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "db8019ba695dd740af7828880d1214aee654454dfc103c50f49753708b15d032", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f8408e5f2efb9b08bc277b51b4a8f2f565fd751402e476a695af00cc52438556", "generation_seconds_batch": 22.45196502597537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05411332845687866, "target_z": -0.43750002435859914, "ce": 6.109982967376709, "genuineness": 4.557555198669434, "identity": 0.6519832611083984, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/db8019ba695dd740af7828880d1214aee654454dfc103c50f49753708b15d032.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "dbc8bd82072fb84221a3939bd2bfb2245b7ae2e6d9353f04286154d54c28ffa5", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "21fed75cfecf0f576bab78ba2e212fb0bf13a619cec82203b10a5d052ab86ab2", "generation_seconds_batch": 21.441346952924505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03977566957473755, "target_z": -0.46093747868622575, "ce": 5.824047088623047, "genuineness": 4.432034492492676, "identity": 0.651120126247406, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/dbc8bd82072fb84221a3939bd2bfb2245b7ae2e6d9353f04286154d54c28ffa5.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "dbf0eb85ab7317dd0693007162e6021c44888c212faac9200dda83b7e0b03fb2", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f10ab620f9906a404dc64e7b5abab0e15dd996f7f2c646c25419d6f406c98c4f", "generation_seconds_batch": 22.77006153203547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3970767259597778, "target_z": 1.757812582210272, "ce": 5.5539960861206055, "genuineness": 3.9048471450805664, "identity": 0.14952121675014496, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/dbf0eb85ab7317dd0693007162e6021c44888c212faac9200dda83b7e0b03fb2.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "dc296c826d197ecafa6dc7748e4a36688aa2c748f0baa98405d4100fc360557c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f466fe28c85d672f2a67eab1a4c6459dfc337b7431f7de8ca65c696a784102ad", "generation_seconds_batch": 21.6153850100236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2238831520080566, "target_z": 3.109374786862258, "ce": 5.959072113037109, "genuineness": 4.005263805389404, "identity": 0.675115168094635, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis portes, dis-moi, tu l'es tata. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.7777777777777778, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/dc296c826d197ecafa6dc7748e4a36688aa2c748f0baa98405d4100fc360557c.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "dc37bfc31e264b81e671cd50b2aa1b00001f4bd33d8bee2fb71d14a4069c92f1", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4d27d444a2b3a6291168ddfaf025d342bba624615d8b41966d526ef006f7504c", "generation_seconds_batch": 22.532724275020882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6157801151275635, "target_z": 3.7500000974343966, "ce": 5.426913261413574, "genuineness": 3.6192874908447266, "identity": 0.45030510425567627, "hypothesis": "La puerta sigue así 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_Fear/dc37bfc31e264b81e671cd50b2aa1b00001f4bd33d8bee2fb71d14a4069c92f1.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "dc8fd06558cc1c241636903fac181015727b150f68de219db67ed279c81ceddd", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "48f2bac0ea35866b7bd364beaa3f72638c89d1505b5a37d129c516b674332ce7", "generation_seconds_batch": 21.483075611991808, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.70180606842041, "target_z": 3.8906248234001564, "ce": 5.486483573913574, "genuineness": 3.6914620399475098, "identity": 0.5205388069152832, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/dc8fd06558cc1c241636903fac181015727b150f68de219db67ed279c81ceddd.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "dcca186c6cef7a0db318f55672cec4044a2b4d60efb86dc4138d0a99c1889528", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d9e63f5e0107850d9317ef8f8d78edae8a2cdda844fbf4138c2a3bdcf151dec0", "generation_seconds_batch": 20.98483688896522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20884087681770325, "target_z": -0.18457031820904668, "ce": 5.7684478759765625, "genuineness": 4.20609712600708, "identity": 0.6516114473342896, "hypothesis": "De deur staat nog opa. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/dcca186c6cef7a0db318f55672cec4044a2b4d60efb86dc4138d0a99c1889528.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "dd192eb66f6d564038441a2c6202b28014b347fcc2c8014c1ca24218287ed8b6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "50b0850139da491d7e1df7483a478c827e52f17d44ca3e94899946cec7b334fd", "generation_seconds_batch": 20.906569999991916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03619122505187988, "target_z": -0.46679689098533067, "ce": 6.070269584655762, "genuineness": 4.281409740447998, "identity": 0.5510240793228149, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/dd192eb66f6d564038441a2c6202b28014b347fcc2c8014c1ca24218287ed8b6.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "dd924fc2ec14bf1e3408eaaceac1f28394a4ad64803ea174208c9a7fc718881d", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f316bcd972083920493b26a99bdd2c2f66e4a40bf8afd25c62518cd294b7cfb5", "generation_seconds_batch": 21.940121141029522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6300104260444641, "target_z": 0.5039062423879378, "ce": 5.95112943649292, "genuineness": 3.9550557136535645, "identity": 0.5279650092124939, "hypothesis": "Ik heb het het kleine doosje gevonden. Het stond naast het oude stond naast het oude raam. We kunnen er samen in kijken.", "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_Fear/dd924fc2ec14bf1e3408eaaceac1f28394a4ad64803ea174208c9a7fc718881d.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": "de204ea1b3bf3ec558335b6e4ae652cfafa2f4c9ab786fa97242825e2bbf7ad0", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "27846e2b3fa12eead6eed2887f38fed4235451f6154a26ef6fda0579feb42563", "generation_seconds_batch": 21.630088313948363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8451831340789795, "target_z": 4.125000146151595, "ce": 5.700935363769531, "genuineness": 3.6475296020507812, "identity": 0.6685889959335327, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/de204ea1b3bf3ec558335b6e4ae652cfafa2f4c9ab786fa97242825e2bbf7ad0.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "de8055c2d5ef4b858f1989b703671c709ace24f3bc8209264afc740ca34eaf84", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "25fd09faa92e5b70f985020250702f48e051d582656e91f7918eefa34c0a8c2d", "generation_seconds_batch": 20.644085936946794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8116211295127869, "target_z": 0.8007812484775876, "ce": 5.911416053771973, "genuineness": 4.557555198669434, "identity": 0.6490147709846497, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/de8055c2d5ef4b858f1989b703671c709ace24f3bc8209264afc740ca34eaf84.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "defca756c51c71b4d0af1627e0f4f15fd88298e1bbdfe58a374949def504fbd1", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5555bcfc2bce306eb5eccc75bab93b2af1d76744e283118afee14db07742ffd8", "generation_seconds_batch": 22.669859299901873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07800948619842529, "target_z": -0.3984375030448249, "ce": 6.205295085906982, "genuineness": 4.720732688903809, "identity": 0.6618741750717163, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/defca756c51c71b4d0af1627e0f4f15fd88298e1bbdfe58a374949def504fbd1.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "df5fc1a3ce4ebe3f14da593e3e73f8dba8a440daee38a35ad7216a988ec27116", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "85f0b9dad15f6b6cfda476c2a5556ac21dd479bf7ca101ec780e8a8bd17ad10a", "generation_seconds_batch": 21.251844824058935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2334418296813965, "target_z": 3.125000146151595, "ce": 5.577824115753174, "genuineness": 3.7291181087493896, "identity": 0.45706069469451904, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/df5fc1a3ce4ebe3f14da593e3e73f8dba8a440daee38a35ad7216a988ec27116.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "df61cc34404e1b6a1d1ee56a925ec7e9897f2835703b039231d322dc22334785", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "bbef951659b35496f4bd3e64c7cb338531f5a6fb31729caa758a22c19812e0b5", "generation_seconds_batch": 20.45713584299665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013489902019500732, "target_z": -0.5039062423879378, "ce": 6.292664527893066, "genuineness": 4.582659721374512, "identity": 0.41998857259750366, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/df61cc34404e1b6a1d1ee56a925ec7e9897f2835703b039231d322dc22334785.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "df6b3b6f2bdb6f6ac53fe4381453935734fcd13ea7938fae412ba588bba01c02", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "032ff24cd7a62d2a70b6487cbb0a5689ba71157bd5ecee5f7e3039984f221bec", "generation_seconds_batch": 23.136461150017567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5690752267837524, "target_z": 0.4042968179095333, "ce": 5.879645347595215, "genuineness": 4.068024158477783, "identity": 0.38285040855407715, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. Ik 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_Fear/df6b3b6f2bdb6f6ac53fe4381453935734fcd13ea7938fae412ba588bba01c02.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "df78e53392ffc91addc726a3424803be91d39bdc16de693ef977e7d39ca2cf91", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6e47bea8389ab1cde7cc15555945d695c1ef07aba8c1216e946a74bf5a79cae2", "generation_seconds_batch": 15.275179378921166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0959851741790771, "target_z": 1.2656248721173546, "ce": 6.078212261199951, "genuineness": 4.099404335021973, "identity": 0.22620631754398346, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/df78e53392ffc91addc726a3424803be91d39bdc16de693ef977e7d39ca2cf91.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "df934fbd769a509f4a665beb9ff5255b2058aef733c8117e7dbf97c8087cce03", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d496274aa86ec3f0f84453962975d2be931b30a581d46cc67817bbef04f36b4c", "generation_seconds_batch": 22.405851930961944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.009959101676941, "target_z": 1.1249999512828017, "ce": 5.839932441711426, "genuineness": 4.3127899169921875, "identity": 0.5869707465171814, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/df934fbd769a509f4a665beb9ff5255b2058aef733c8117e7dbf97c8087cce03.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": "dfc3e3d6be7351cef924d9e2f7356cd190feb208f77592e2094b60f5d214b6ec", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e561f58b3327d8af7c969d6fb82d338da11acc8a43876502a321a50588690024", "generation_seconds_batch": 14.555862723034807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05411332845687866, "target_z": -0.43750002435859914, "ce": 6.332377910614014, "genuineness": 4.2374773025512695, "identity": 0.5325811505317688, "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_Fear/dfc3e3d6be7351cef924d9e2f7356cd190feb208f77592e2094b60f5d214b6ec.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "dfdae79a7a3b1fe95bfd0f65b38f1fa7339184dc2ca1be06b700623f378d559f", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "45e15bf7bbdc6e1dea89b4380bda8e18233728e93e8982402a17c6ce32ddee3f", "generation_seconds_batch": 16.370319727924652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08517833054065704, "target_z": -0.3867187515224124, "ce": 6.229123115539551, "genuineness": 4.381826400756836, "identity": 0.6721180081367493, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/dfdae79a7a3b1fe95bfd0f65b38f1fa7339184dc2ca1be06b700623f378d559f.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "e05b0b416b3c550ed85f901eb68c0c08425cd9c903298693e8ae1ddf72dec63e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "26dde975498afb4d5a1a29012db387f778bd1fd495aee88fe8165624159a1293", "generation_seconds_batch": 21.485096354037523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.787832260131836, "target_z": 4.031249939103502, "ce": 5.403085231781006, "genuineness": 3.6412534713745117, "identity": -0.09137861430644989, "hypothesis": "De deur 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_Fear/e05b0b416b3c550ed85f901eb68c0c08425cd9c903298693e8ae1ddf72dec63e.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": "e089c23331d6d1b9b2c17a44b6b137c891e44b5910ee7eccab1e2c4edd8a4bf1", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c3c193405fbf17ea5e2e88dab64cc4c259a44dc9ef3da997f1b0b3d53e3e936d", "generation_seconds_batch": 16.996140163042583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3863770961761475, "target_z": 3.3750000487171983, "ce": 6.022613525390625, "genuineness": 4.093128204345703, "identity": 0.5557829141616821, "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_Fear/e089c23331d6d1b9b2c17a44b6b137c891e44b5910ee7eccab1e2c4edd8a4bf1.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "e09465cd415050e1beef2a25f68d9cfe20db73a6f5c3960fa90a1d2ad4b29f19", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0244ee24c3c568789b02015bb14309a44b666de0e2e9c810e4961944759a353b", "generation_seconds_batch": 20.126898562069982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8834168910980225, "target_z": 4.187500024358599, "ce": 5.748591423034668, "genuineness": 3.6851859092712402, "identity": 0.5355640649795532, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/e09465cd415050e1beef2a25f68d9cfe20db73a6f5c3960fa90a1d2ad4b29f19.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "e0e76a23018f8c33ac02731f1c059ccd88c469e2e83ee037778e379c8859d02a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4fbfd81c1a5547c30a443b7ca603ac69a4add04004745e33cc5c4342c237114b", "generation_seconds_batch": 22.23943150800187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.596663236618042, "target_z": 3.718750158330894, "ce": 5.77639102935791, "genuineness": 4.193545341491699, "identity": 0.7160859107971191, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons garder 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_Fear/e0e76a23018f8c33ac02731f1c059ccd88c469e2e83ee037778e379c8859d02a.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "e102cb7821a2611de2a1422ca2fa2f9b78e1cd22b884896aa6aef6c1e2d0b33d", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6f5bad046ce5a42e2c4e799e8141dcbac32cde89bfa103d5e16ea747d0dd8f11", "generation_seconds_batch": 20.93115697999019, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6025835275650024, "target_z": 2.0937500121792993, "ce": 5.935244083404541, "genuineness": 4.042920112609863, "identity": 0.5648428201675415, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast 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_Fear/e102cb7821a2611de2a1422ca2fa2f9b78e1cd22b884896aa6aef6c1e2d0b33d.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "e12829f561d370949c3250d97d0f892daed483ad7961654ceddaf38ca66c17a5", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2e537b2ecb603b3939ecab01a9b9eb2548e56ff2dac7cae4f11e884e45cb7263", "generation_seconds_batch": 21.251844824058935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1187400817871094, "target_z": 2.93749973205541, "ce": 4.934467792510986, "genuineness": 3.503180742263794, "identity": 0.4368737041950226, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster! Wir können gemeinsam hineinschauen!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/e12829f561d370949c3250d97d0f892daed483ad7961654ceddaf38ca66c17a5.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "e1dcd915eea5bb1537eccc67d12e77d7cf15f09e3fb81ce77f5634231f825154", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "42ac5d782ade3807b8c9f137072ed22b6ffbe7c345200c20c3fbf8637975d685", "generation_seconds_batch": 20.662580291973427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006321042776107788, "target_z": -0.5156250182689494, "ce": 6.1894097328186035, "genuineness": 4.074300289154053, "identity": 0.4540081024169922, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/e1dcd915eea5bb1537eccc67d12e77d7cf15f09e3fb81ce77f5634231f825154.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "e23666ef451447f28c9fcc2275f40dfc3873f2f95cff5193e3d38c1c2cf66690", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "628604647a68972f12dc527272ef8cde0a5d6fe95b93f576c267545cffd31f32", "generation_seconds_batch": 22.06744200293906, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025437980890274048, "target_z": -0.48437498173105065, "ce": 6.1894097328186035, "genuineness": 4.821148872375488, "identity": 0.8092193603515625, "hypothesis": "J'ai trouvé la 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_Fear/e23666ef451447f28c9fcc2275f40dfc3873f2f95cff5193e3d38c1c2cf66690.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "e26cf1cb1f418a734e18981b69d3c17943e1265fb43a1d372ebfd3eb48808f0d", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e594d4ce2eaa04bb2f0215b63f6b87efa4b6e597e87fc2334a68d298b28c634b", "generation_seconds_batch": 22.729310101014562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7757769227027893, "target_z": 0.7421875152241244, "ce": 5.863759994506836, "genuineness": 4.287685871124268, "identity": 0.573584794998169, "hypothesis": "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_Fear/e26cf1cb1f418a734e18981b69d3c17943e1265fb43a1d372ebfd3eb48808f0d.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": "e2750d5c044c5d7525d90c6067204f54f1d215cd8763443dd1b22d26b3bfd2b2", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3cbbdac218ceb2b486129481efe1591481af3ecb0dd10b5345245e0a085ccc15", "generation_seconds_batch": 14.686002915957943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8797787427902222, "target_z": 2.546874908655253, "ce": 6.117925643920898, "genuineness": 3.8044304847717285, "identity": 0.3898128867149353, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/e2750d5c044c5d7525d90c6067204f54f1d215cd8763443dd1b22d26b3bfd2b2.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "e277baed09e1f4e8975d41bd70ea9e50048b52a8c97059d969195bb6853b33ac", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e13b0eeab4dfc89af38f4979819c5e346ba5d4a04f0a368984f1ba5f5a095f0d", "generation_seconds_batch": 20.498536992934532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5930250883102417, "target_z": 2.0781250426275486, "ce": 5.593709468841553, "genuineness": 4.193545341491699, "identity": 0.7090030312538147, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den. Sag mir, wenn du bereit bist.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/e277baed09e1f4e8975d41bd70ea9e50048b52a8c97059d969195bb6853b33ac.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": "e3668c51eaa28b9a3f7d16577a5747c1bf970b1d3b933a467d4172628aa9038c", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ff695749efacb7f5ba244e910a90aca49fbb379865486692758131fe0f410df8", "generation_seconds_batch": 22.055939739919268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.208404541015625, "target_z": 4.718750158330894, "ce": 5.5738525390625, "genuineness": 3.3964879512786865, "identity": 0.5896135568618774, "hypothesis": "La route tourne à gauche, après le pont, continue jusqu'à l'à la petite barrière, en bois. Je t'attendrai de l'autre côté.", "wer": 0.05, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/e3668c51eaa28b9a3f7d16577a5747c1bf970b1d3b933a467d4172628aa9038c.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "e3cbb7cfb8552e3a6b00fb38608bb209b89d5ddc9c626cd28d371f89f86c2738", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b0986b401550fbabb8c70b94afb5cda480ef00c6e2e021bac8892aef7b1dc3e8", "generation_seconds_batch": 14.353676731116138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.621700406074524, "target_z": 2.1249999512828017, "ce": 6.078212261199951, "genuineness": 4.074300289154053, "identity": 0.5888933539390564, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen. Falls Metonky Boss ist Heta! Wir können gemeinsam hineinschauen.", "wer": 0.5625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/e3cbb7cfb8552e3a6b00fb38608bb209b89d5ddc9c626cd28d371f89f86c2738.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "e41508c79bef6f79212be0e887b3ae09aaa8bb4215e17a0aceea8716faf0a77b", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0a6f4a5376485be4162f09b2b67391279407de7d6a5766453c2fc1c85baa015f", "generation_seconds_batch": 20.41035237594042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.434169292449951, "target_z": 3.4531248964759538, "ce": 5.824047088623047, "genuineness": 4.049196243286133, "identity": 0.7522693872451782, "hypothesis": "J'ai trouvé, j'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/e41508c79bef6f79212be0e887b3ae09aaa8bb4215e17a0aceea8716faf0a77b.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "e49333b8ac88684ca6c8c17c8299e242584427756cf4599c3fba1b6aff969fae", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e7a29408d4c6f10ea3cfec244a728ca1469432f6b38ab31061fda5ba93439093", "generation_seconds_batch": 21.280625435058028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.099623203277588, "target_z": 2.9062497929519076, "ce": 5.478540420532227, "genuineness": 3.578493118286133, "identity": 0.22193744778633118, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent. Zeg maar wanneer ik klaar bent.", "wer": 0.3157894736842105, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/e49333b8ac88684ca6c8c17c8299e242584427756cf4599c3fba1b6aff969fae.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": "e4d1001cde7845ec61aeae068cb696cb1b6a0f7e060b8f0ccaff45527f50c453", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "33ee4e6052103ed0d39a5e686fcf280e6def854b33e36d4fbd1ca2e932f59740", "generation_seconds_batch": 21.230915053980425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.70180606842041, "target_z": 3.8906248234001564, "ce": 5.748591423034668, "genuineness": 3.747946262359619, "identity": 0.64593505859375, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/e4d1001cde7845ec61aeae068cb696cb1b6a0f7e060b8f0ccaff45527f50c453.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "e4ffdacbebaa5dbc8afee19c98c48c57c785d9401d7f098d1e71d5755ad8e78c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0b3a499c00d6b51d7161a37599eb98bf7e3275276a31981271fa5be91f315f95", "generation_seconds_batch": 22.255350062041543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.548870801925659, "target_z": 3.640624920834553, "ce": 5.720792293548584, "genuineness": 4.137060642242432, "identity": 0.35844099521636963, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/e4ffdacbebaa5dbc8afee19c98c48c57c785d9401d7f098d1e71d5755ad8e78c.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "e50efdd29986e8d182628ce3aa68acbd9f5264b23680cdec63eecbeabffda491", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4c11cd6347fe6ec5a2652aab11acd4eba73bc6918ca8b33c51b2babfd4e1599e", "generation_seconds_batch": 23.882364302990027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0481929779052734, "target_z": 1.1875000243585991, "ce": 5.569881439208984, "genuineness": 4.306513786315918, "identity": 0.49292778968811035, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/e50efdd29986e8d182628ce3aa68acbd9f5264b23680cdec63eecbeabffda491.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "e5824ca82b5c0c6e344ecd5b4987e0cd22d993ef240e84a784b0250caad536f0", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "40ecdbb2d646739a2391b2f8d3784b3e9160576c9c8a8b9591fd95a92dc2a941", "generation_seconds_batch": 21.472937868908048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1210225522518158, "target_z": -0.3281249939103502, "ce": 6.181467056274414, "genuineness": 4.457139015197754, "identity": 0.6854536533355713, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/e5824ca82b5c0c6e344ecd5b4987e0cd22d993ef240e84a784b0250caad536f0.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "e5f21eace4de1b6497bfd6783de9f53dcca2ee3de8826e4d16308945d88975be", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "325eab27d4dfdbe7aa2025262cae8848b646c70242983d357f9878bab3a6884e", "generation_seconds_batch": 20.95479655591771, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14730830490589142, "target_z": -0.2851562545672373, "ce": 5.8875885009765625, "genuineness": 4.319066047668457, "identity": 0.6103780269622803, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/e5f21eace4de1b6497bfd6783de9f53dcca2ee3de8826e4d16308945d88975be.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": "e66abaf58bd9cfb546378c245f248b69ca8f138711c1c88771dcfa57f25871bc", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 133, "seconds_generated": 10.64, "mp3_sha256": "4d2007f4cf9ee8a7a90b76c906e5c6f8fe8f02411da7e9fd1ac18d826df5758a", "generation_seconds_batch": 18.701524717966095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9753633737564087, "target_z": 2.7031249939103503, "ce": 5.895530700683594, "genuineness": 3.9299514293670654, "identity": 0.7120885848999023, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir plus près de la fenêtre. Prends-les quand tu partiras. Misty je symboloski. Boum ! Les clés sont sur la table de la cuisine.", "wer": 0.5833333333333334, "duration_error_s": 0.4400000000000013, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/e66abaf58bd9cfb546378c245f248b69ca8f138711c1c88771dcfa57f25871bc.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "562259991fb1ec3628e337e46ef17508b8e40b68419d50b3fb551d478c75b235", "generation_seconds_batch": 16.598602466052398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024243175983428955, "target_z": -0.48632810292501955, "ce": 6.435632705688477, "genuineness": 4.444586753845215, "identity": 0.2598378658294678, "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_Fear/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "e7504effc7738b47bae87fc42e859b93df1bed125578f3e076a05db2ce2350a3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "dbe9fa378427aed94759be1ffc6fd97064a7c9fc17c73642028c82bdb8f1e199", "generation_seconds_batch": 21.17353564000223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.055469036102295, "target_z": 4.4687498660277045, "ce": 6.006728172302246, "genuineness": 3.5722172260284424, "identity": 0.38092631101608276, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/e7504effc7738b47bae87fc42e859b93df1bed125578f3e076a05db2ce2350a3.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "e7d4edfa6556f1d5f4225ab2ff369b70078e9b10f73ae94f5d396be49a5b147e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "70fac9e3ca94bc6426e1b9027baefc20c7cc9f186f36be8dce317eb018eac1ef", "generation_seconds_batch": 15.275179378921166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43943867087364197, "target_z": 0.19238280298492222, "ce": 5.77639102935791, "genuineness": 4.036643981933594, "identity": 0.23877334594726562, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/e7d4edfa6556f1d5f4225ab2ff369b70078e9b10f73ae94f5d396be49a5b147e.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": "e8669f92b281e4db0c58b62f23651367db390bdb33ba7da87c4c36dcfbc278a2", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5e217a5bad3cdada2f5a1ccb767a674fdc3a18916e9593b95bbbb93f93e8c0cc", "generation_seconds_batch": 16.22633032500744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4424256980419159, "target_z": 0.19726563032844355, "ce": 5.788304805755615, "genuineness": 4.507347106933594, "identity": 0.715868353843689, "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_Fear/e8669f92b281e4db0c58b62f23651367db390bdb33ba7da87c4c36dcfbc278a2.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "4165046462e2d97e18790003cd64c32c4c4ce0089b95886e227bd982c5d2fe28", "generation_seconds_batch": 16.677892565028742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.060087382793426514, "target_z": -0.4277343696715564, "ce": 6.221180438995361, "genuineness": 4.570107460021973, "identity": 0.48914408683776855, "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_Fear/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "e9ea2cda01b1465a5131d05fa556f3de01e217e751527641f1a8fd29e00cead0", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e881c77002286f5704ee4c9c12220df68605832146e16b1584f4464d2930f432", "generation_seconds_batch": 14.869468888966367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.583466649055481, "target_z": 2.0625000730757974, "ce": 5.605623245239258, "genuineness": 3.4969046115875244, "identity": 0.3790613114833832, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear/e9ea2cda01b1465a5131d05fa556f3de01e217e751527641f1a8fd29e00cead0.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "ea3ba3a2a07194af510ea560fff97f3f48a839a24d4166c2d98108a768ddb150", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "39871406bc2fb789fdadebd678cd269a44bcab79c584c6a30cd82cc1a3eb69e5", "generation_seconds_batch": 25.715901441057213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0805063247680664, "target_z": 2.874999853848405, "ce": 5.704906940460205, "genuineness": 3.9801597595214844, "identity": 0.7070658206939697, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi où 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_Fear/ea3ba3a2a07194af510ea560fff97f3f48a839a24d4166c2d98108a768ddb150.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "ea990f3b0d9c85a4698bb231c9d4d69a7069a6ff65c8b184f5e1c3c827a2a082", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7aea6b6b6f161143d88e35b85b5b6b9edc2c7f85cf5a069642b47be8a3e97f20", "generation_seconds_batch": 20.714859631028958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.027133554220199585, "target_z": -0.5703125091344746, "ce": 6.332377910614014, "genuineness": 4.457139015197754, "identity": 0.5356836318969727, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ea990f3b0d9c85a4698bb231c9d4d69a7069a6ff65c8b184f5e1c3c827a2a082.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": "eac16a825d5bf366c19b8edb6cce3e41591f1df7b45d7b9d52b2f2857342a78f", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8f6bc79fd399b71689aa6baa24c2fcd9ca42ecf075a84119e194d32797048145", "generation_seconds_batch": 15.525528879021294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4150524139404297, "target_z": 3.4218749573724514, "ce": 5.895530700683594, "genuineness": 3.8671910762786865, "identity": 0.5459499359130859, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous ne la remettrons qu'après le déjeuner.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/eac16a825d5bf366c19b8edb6cce3e41591f1df7b45d7b9d52b2f2857342a78f.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "eb502f25e874e8610f62a3877637d33330b26b283995677382e9d3d8fb73be60", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a6aaf193c84bad7a1e676d0d36c98189b5639e2d6abc908a96e8b2eb52455289", "generation_seconds_batch": 16.01190444303211, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.290792465209961, "target_z": 3.2187499634621015, "ce": 5.911416053771973, "genuineness": 3.3996260166168213, "identity": 0.41795575618743896, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/eb502f25e874e8610f62a3877637d33330b26b283995677382e9d3d8fb73be60.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": "eb6745f55becf8f1aab8737b1ac8474a12383cd9c66dbe651962b757e732e1be", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ec8819a875286148a58b07c740fe2f3e8e86942ec12e85ccda9070204119a6bb", "generation_seconds_batch": 21.8380950599676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.826066017150879, "target_z": 4.093749817310506, "ce": 5.4666266441345215, "genuineness": 3.9801597595214844, "identity": 0.690567135810852, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi quand nous pouvons parler.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/eb6745f55becf8f1aab8737b1ac8474a12383cd9c66dbe651962b757e732e1be.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "76e26b8429834e53eb2482aba09d0373cccefbddfa82843c176b8557ad7bd43c", "generation_seconds_batch": 15.791826182045043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046944499015808105, "target_z": -0.4492187515224124, "ce": 6.181467056274414, "genuineness": 4.507347106933594, "identity": 0.7841650247573853, "hypothesis": "La route tourna gauche après le pont. Continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.1, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "ec10e5fd033cb7ff576175a1447ec6b11f0ab5952d3bb3761b53c8880996fc8c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "23fe044a7d83028a81ba50e73230f925acd8947eacfda0764e1a591dffe4842f", "generation_seconds_batch": 19.677496960037388, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7304816246032715, "target_z": 3.9375001217929957, "ce": 5.911416053771973, "genuineness": 3.575355052947998, "identity": 0.23647387325763702, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ec10e5fd033cb7ff576175a1447ec6b11f0ab5952d3bb3761b53c8880996fc8c.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "ed55cd4e6a6afe1679419e7b4fde918a44dd36f09d7ed37963e4942054ff6f35", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cbead94439f252cf5ae67232658eb322c8b96a851627a0a01ec11c8ff6387fd7", "generation_seconds_batch": 21.647727917996235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.520195484161377, "target_z": 3.5937500121792993, "ce": 5.454712867736816, "genuineness": 3.9299514293670654, "identity": 0.5810216665267944, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ed55cd4e6a6afe1679419e7b4fde918a44dd36f09d7ed37963e4942054ff6f35.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "ee0ae4892c9ea6493216560158aeedb654f78c26f0b27f4ffe5577a62d766ce5", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "596cb6702b00807929000cc60bab037a330246ae7b6bc5ec7719d762a45e90b0", "generation_seconds_batch": 22.79071933205705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4246108531951904, "target_z": 3.4374999269242026, "ce": 5.39911413192749, "genuineness": 4.2374773025512695, "identity": 0.7342632412910461, "hypothesis": "La porte est encore ouverte. J'ai posé tout le manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.1111111111111111, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ee0ae4892c9ea6493216560158aeedb654f78c26f0b27f4ffe5577a62d766ce5.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "ee17c92e3c0a5c141bae6d50bdbe2b6763b8b24fca55865a314e65ce059ebc86", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2c1980bf07436c018ad57f932518140c8c45a2ca4f1367d51408f1dd25da6318", "generation_seconds_batch": 14.869468888966367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6981680393218994, "target_z": 2.2499999025656034, "ce": 5.696964263916016, "genuineness": 3.8169827461242676, "identity": 0.14761880040168762, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ee17c92e3c0a5c141bae6d50bdbe2b6763b8b24fca55865a314e65ce059ebc86.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "ee38c824d2c33e513865beb437fefa96824bd3bdf94339c6f2ff78d458a9e259", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "05417e0b938130d77394af3b8e183ae5b59c5953d3285da3989da6838d9fc658", "generation_seconds_batch": 21.52749768598005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21720454096794128, "target_z": -0.17089842113406623, "ce": 5.863759994506836, "genuineness": 4.444586753845215, "identity": 0.4165307879447937, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. Vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ee38c824d2c33e513865beb437fefa96824bd3bdf94339c6f2ff78d458a9e259.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "ee74e8888f2596da29e82adc4d2fa8cc9c62e353c2886fb8118a9321266ea0d2", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e0cc73bb1f204aa0b56454463fc3248673256c0ddd61f873790ddb272b0e0fe6", "generation_seconds_batch": 16.365282217040658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.010406255722045898, "target_z": -0.542968763701712, "ce": 6.308549880981445, "genuineness": 4.570107460021973, "identity": 0.6077717542648315, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ee74e8888f2596da29e82adc4d2fa8cc9c62e353c2886fb8118a9321266ea0d2.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "ee869a41c90ef220e6db67799013bfbafeb898f743883f47fdfaee2f968989ab", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "65b546531d78f6211b8083ce42c1c9823fda88af7a44fc92202119dc8eeba798", "generation_seconds_batch": 15.784480702015571, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8606618642807007, "target_z": 2.515624969551751, "ce": 5.895530700683594, "genuineness": 4.20609712600708, "identity": 0.38943612575531006, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ee869a41c90ef220e6db67799013bfbafeb898f743883f47fdfaee2f968989ab.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": "ef828a96fda79b0d372d22281f3d1ac9977d22742ba5715d1efd52c7e6a220bf", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a32b547cdb503a08c8486081c6d7e2d562ec00e09dbca3529ca03befb0dfd809", "generation_seconds_batch": 21.57515984098427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8415449857711792, "target_z": 2.484375030448249, "ce": 5.720792293548584, "genuineness": 3.8295347690582275, "identity": 0.7081847190856934, "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_Fear/ef828a96fda79b0d372d22281f3d1ac9977d22742ba5715d1efd52c7e6a220bf.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "efcc7a2bb717468ae78e9f740d405ed73de47db84f67d40d9bc839b4ad4763e8", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ac4dfd2201d13e689a3fa1cce463dbc845b9e7efb82f73de02404048374d1591", "generation_seconds_batch": 20.272556668962352, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5930250883102417, "target_z": 2.0781250426275486, "ce": 5.534139156341553, "genuineness": 4.149612903594971, "identity": 0.2347005307674408, "hypothesis": "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_Fear/efcc7a2bb717468ae78e9f740d405ed73de47db84f67d40d9bc839b4ad4763e8.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "f057ed43ffd9e9d525e2884393ee79ae400054be73f454f1dddfe80a004a06e3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4916cbf84bf5ec68d31ca34bdd8156e0c5246c311a536f78e9eaee6524d84ce4", "generation_seconds_batch": 21.61805590800941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10071082413196564, "target_z": -0.3613281272836187, "ce": 6.038498878479004, "genuineness": 4.494794845581055, "identity": 0.4857568144798279, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f057ed43ffd9e9d525e2884393ee79ae400054be73f454f1dddfe80a004a06e3.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "f079ab06749fb22a3369267e53112378efc5a1dbcb0367fa465889e2cd73509d", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "424414ff088ce8ec961658231d508defb573982df53f23621d3066d397937200", "generation_seconds_batch": 22.555160978925414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03619122505187988, "target_z": -0.46679689098533067, "ce": 6.022613525390625, "genuineness": 4.482243061065674, "identity": 0.49619317054748535, "hypothesis": "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_Fear/f079ab06749fb22a3369267e53112378efc5a1dbcb0367fa465889e2cd73509d.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "f126a17f19c902546ac13bc3978e0d52e56350c91196e4b617626dd16945e6d6", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "99db52eafcccd4805bb4bb7ea05c22ee472157e32507d7a42db6287a3980d4f8", "generation_seconds_batch": 21.414594050031155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18972396850585938, "target_z": -0.2158203060297471, "ce": 6.252951145172119, "genuineness": 4.375550270080566, "identity": 0.7282936573028564, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f126a17f19c902546ac13bc3978e0d52e56350c91196e4b617626dd16945e6d6.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": "f1ecef12254051df79bcc23c989c89ea82cc5f86132a066860e7bd5ce67d94f5", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "baece0abcaf1dd9e90ce61c0139377af8111e8155a8f0b47fd5e3aeb5ba3742c", "generation_seconds_batch": 16.0854093269445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15447714924812317, "target_z": -0.2734375030448249, "ce": 6.078212261199951, "genuineness": 4.15588903427124, "identity": 0.5972753167152405, "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_Fear/f1ecef12254051df79bcc23c989c89ea82cc5f86132a066860e7bd5ce67d94f5.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "5dab650429446d885bc6dd01f7220d8f745b3324cae75e338b406c639a32ebce", "generation_seconds_batch": 15.872273468994536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.061282187700271606, "target_z": -0.4257812484775876, "ce": 6.125868320465088, "genuineness": 4.507347106933594, "identity": 0.777224063873291, "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_Fear/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "f2343d0b760cbfcb01ab35022b4562bcb0e500c929a142f49107ffe8515dc16c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9609ac97b5d19df6de1a7da44df5d36949b632c3bd62f691a7d9ca3619cf71c1", "generation_seconds_batch": 20.50147660204675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6539065837860107, "target_z": 0.542968763701712, "ce": 6.173524379730225, "genuineness": 4.030367851257324, "identity": 0.6520954370498657, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f2343d0b760cbfcb01ab35022b4562bcb0e500c929a142f49107ffe8515dc16c.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": "f238dd9281a2dd08f50bcabed8e2957c3ba4a0521a40bf5af74348bc7c8cd5af", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "486961d79ac246ab2056bfc824e720b46696ad724587e7651db4f5ed99ffaa4e", "generation_seconds_batch": 15.508048248011619, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5871047973632812, "target_z": 3.703125188779143, "ce": 5.665193557739258, "genuineness": 3.8797430992126465, "identity": 0.720115065574646, "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_Fear/f238dd9281a2dd08f50bcabed8e2957c3ba4a0521a40bf5af74348bc7c8cd5af.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "f23f960c18b0321ae04cee91dadf6c81afdc938c7fe3e8d23bcfdba00851d206", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5616c3b47f57e345f307bef30021c300c355bd186a2745ed0dffff861186cdce", "generation_seconds_batch": 21.45383932197001, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8570238351821899, "target_z": 0.8750000487171983, "ce": 5.510311126708984, "genuineness": 4.300237655639648, "identity": 0.541110634803772, "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_Fear/f23f960c18b0321ae04cee91dadf6c81afdc938c7fe3e8d23bcfdba00851d206.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": "f2608bfd94283eb1ac1716aa62007a8daa5fcd333d4ae75774db85ff7fd5cb12", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7b4af253e879dfa8adce2990df3518581384f39f470978ced6e0cc1a7748119e", "generation_seconds_batch": 21.121772763086483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.258479118347168, "target_z": 1.531250133972295, "ce": 5.0774359703063965, "genuineness": 3.9173994064331055, "identity": 0.394694983959198, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich lass sie zweimal. Dann legte ich das hier nicht weg. Sag mir, was wir reden können.", "wer": 0.16666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f2608bfd94283eb1ac1716aa62007a8daa5fcd333d4ae75774db85ff7fd5cb12.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "f2b3a45ea4e50b48bb41cb402123a064803f4554558aa8100326929c6de0407c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e2ab234b5639dafd99d70782bc4857e2bd8143b72c833ee12059a95c0556e3e5", "generation_seconds_batch": 15.023613129975274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32921770215034485, "target_z": 0.01220701964160511, "ce": 5.895530700683594, "genuineness": 4.557555198669434, "identity": 0.579276442527771, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f2b3a45ea4e50b48bb41cb402123a064803f4554558aa8100326929c6de0407c.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "f2ef8c70d507f0b90353ac087f69f79f7a481d1b5a1465c34bf3a6826f50406f", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9a120b8d468359f29a6a8544c0dd1c1203319ffc597c4acab9aa6d4b276fe7e0", "generation_seconds_batch": 22.444250102038495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47707509994506836, "target_z": 0.2539062423879378, "ce": 6.006728172302246, "genuineness": 4.15588903427124, "identity": 0.5610856413841248, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f2ef8c70d507f0b90353ac087f69f79f7a481d1b5a1465c34bf3a6826f50406f.mp3" }, { "id": "emo_Fear-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, 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_Fear-de-0", "key": "f305428f6d03822b400cbe3eefeef5c49bd96cd4ce75c6cc204cde19b9d8e430", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5fcf026000da6313fd2a5ad163ba8e6cdbbc50bdbb9d5e7dced4a49377ed2b2f", "generation_seconds_batch": 20.498536992934532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7077265977859497, "target_z": 2.2656250669861477, "ce": 5.262103080749512, "genuineness": 4.13078498840332, "identity": 0.4523010551929474, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f305428f6d03822b400cbe3eefeef5c49bd96cd4ce75c6cc204cde19b9d8e430.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "f3116c69d5be22d2e605cb3d167a87b4fb7578382c466e0c304ec457726b46dc", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "86612cc562d619bec6ede479ccd21f82912094101e32dcb213957bf3ea993176", "generation_seconds_batch": 22.17413131892681, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9765045046806335, "target_z": 1.0703124604172765, "ce": 4.725972652435303, "genuineness": 3.9801597595214844, "identity": 0.5927671194076538, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem Erdenfenster. Wir könnten gemeinsam hineinschauen.", "wer": 0.1875, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f3116c69d5be22d2e605cb3d167a87b4fb7578382c466e0c304ec457726b46dc.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "f3166cafd958f654f1acacf3b0677dc41fe1bf37e11f3abcfbc9e1db0903cc0e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d0a33db5fcdcb21a6d0372e3f0bd61865c58face93b56b28db6b87344c24cca4", "generation_seconds_batch": 22.30231169704348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3474385142326355, "target_z": 0.04199217874612844, "ce": 6.054384231567383, "genuineness": 4.362998008728027, "identity": 0.5526118874549866, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f3166cafd958f654f1acacf3b0677dc41fe1bf37e11f3abcfbc9e1db0903cc0e.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "f322194c38fa628558ccfaecc276da1b9080b6d9a340a8f0c437c46bafc6977c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "eb99f1a15a8c1c0512af9e1ae414fecca778f5074dcd0ce10ebcef350b7328ed", "generation_seconds_batch": 16.731221021036617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08756794035434723, "target_z": -0.3828125091344747, "ce": 6.24500846862793, "genuineness": 4.068024158477783, "identity": 0.4926965832710266, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f322194c38fa628558ccfaecc276da1b9080b6d9a340a8f0c437c46bafc6977c.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": "f394eb70cb7aa0c48fd584293e61fa9e901d362effc2a8b2479bdef7a163c610", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5349107442a59b8130b79e086f1909df7f2dd4cdb065f5ae6fd8f6f7c1e4d73f", "generation_seconds_batch": 16.270587361999787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8606618642807007, "target_z": 2.515624969551751, "ce": 6.0305562019348145, "genuineness": 4.218649387359619, "identity": 0.5657484531402588, "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_Fear/f394eb70cb7aa0c48fd584293e61fa9e901d362effc2a8b2479bdef7a163c610.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "f3b599c2a897c5ac8d51ddc84ebd5e64cf232040b5d9380ea39bdf432cb0faa2", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0ec4e7c280fb8bf413bd35dddee91dcbf975833ea480e2d5f7aa873f4942e2f1", "generation_seconds_batch": 21.63867566292174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3385846614837646, "target_z": 3.296874811220857, "ce": 5.657250881195068, "genuineness": 3.785602569580078, "identity": 0.11914591491222382, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen dus samen in.", "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_Fear/f3b599c2a897c5ac8d51ddc84ebd5e64cf232040b5d9380ea39bdf432cb0faa2.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "f3e95a5daad79b64dc29691a141a58dd44ca3988ae9b322d6d5548ef90cd1ebd", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3460f1d56cbf2be6adbf2db68fcf7d674b8f8003c9e6bea188ab89e0b2ccfa3b", "generation_seconds_batch": 23.55888942000456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7400400638580322, "target_z": 3.953125091344747, "ce": 5.395142555236816, "genuineness": 4.017816066741943, "identity": 0.5864308476448059, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons garder ensemble plus ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f3e95a5daad79b64dc29691a141a58dd44ca3988ae9b322d6d5548ef90cd1ebd.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": "f4634f9e005308e354b14e07807ff5f4e1da3d7fdf073cbff2306266f8536d85", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "47e4ffc00e12398a6c1d51fef6c584704a9b575a5a679ca668b45478733857ea", "generation_seconds_batch": 16.481527063064277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11743812263011932, "target_z": -0.333984381850856, "ce": 6.062326908111572, "genuineness": 4.287685871124268, "identity": 0.5246391296386719, "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_Fear/f4634f9e005308e354b14e07807ff5f4e1da3d7fdf073cbff2306266f8536d85.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "f48fb05e7da310e76a14aed794357d33e090a1fe45df36a5eebb6e218b7b59b3", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f21398158a2aee42234a12a1507e33fa3a39b4abbcd632509e0eefecd682ec1f", "generation_seconds_batch": 21.6153850100236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3540099561214447, "target_z": 0.052734369671556446, "ce": 6.165581703186035, "genuineness": 4.482243061065674, "identity": 0.5793329477310181, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Sur les portes est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.7222222222222222, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f48fb05e7da310e76a14aed794357d33e090a1fe45df36a5eebb6e218b7b59b3.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "f4c56569e45d6b118d860e34322c96d6844537d6bd90dfc5d8c2f9f396f038cc", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "39689e2d3082370743566db3c67dca9c455a6eee2a543b14db4ba2f51d5fe725", "generation_seconds_batch": 15.437776311999187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0004006624221802, "target_z": 1.1093749817310508, "ce": 5.982900142669678, "genuineness": 4.331617832183838, "identity": 0.6880896091461182, "hypothesis": "J'ai trouvé la petite boîte. Elle était prête. La vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f4c56569e45d6b118d860e34322c96d6844537d6bd90dfc5d8c2f9f396f038cc.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "f4d6c57d5595d49799660b600ba11edc96cac3193dfecd9b3bda2941b11f288c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0851f884989052c5c682d9b30c7e05dae15b3dd45ec909f5f843356abf0f7aeb", "generation_seconds_batch": 20.04254691605456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3481433391571045, "target_z": 3.312500170510194, "ce": 5.442798614501953, "genuineness": 3.503180742263794, "identity": 0.4796559512615204, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f4d6c57d5595d49799660b600ba11edc96cac3193dfecd9b3bda2941b11f288c.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "f4dd8c36d5be5ec649a38038aa9b78e09a20d10b30828fee2379931052269127", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "466947bfda0f2f7f3f4f924df91e82a66a989f103bdc9fb291607ff8e02d73aa", "generation_seconds_batch": 20.125497277942486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7160365581512451, "target_z": 0.6445312606568872, "ce": 6.221180438995361, "genuineness": 4.281409740447998, "identity": 0.5092708468437195, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f4dd8c36d5be5ec649a38038aa9b78e09a20d10b30828fee2379931052269127.mp3" }, { "id": "emo_Fear-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We 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_Fear-en-1", "key": "f5094e669e2f886007a9644d186c683dbb8fb00efe365ea33fc35bb109468fe2", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] I found the little box.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] It was beside the old window.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7b2c4eefbed27c3109da9d1135f43587753f7a16700d940c5ea04ce899fccf93", "generation_seconds_batch": 22.18869847105816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12580177187919617, "target_z": -0.3203125091344747, "ce": 5.998785495758057, "genuineness": 4.268857479095459, "identity": 0.5590690970420837, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f5094e669e2f886007a9644d186c683dbb8fb00efe365ea33fc35bb109468fe2.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "f635400c9902f14c868b1ac5aff9bd07a14da294da62fe45c8c95c95775401be", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ce706bd245f9062dbaeb3b18724b218fca72c8f1fc3d2bd3e3fe87616b2832ac", "generation_seconds_batch": 20.857606638921425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.625338554382324, "target_z": 3.7656250669861477, "ce": 5.9431867599487305, "genuineness": 3.5188708305358887, "identity": 0.7158329486846924, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f635400c9902f14c868b1ac5aff9bd07a14da294da62fe45c8c95c95775401be.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "f6814d2e97cdded85876cfe4a5204ae40b52dedce65652cc26966768abae3697", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4f699815a18ac59ea856ce197b0534384d3f764a2ff226a7ac61bc6c6c60013e", "generation_seconds_batch": 14.353676731116138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.902533769607544, "target_z": 4.218749963462101, "ce": 5.728734970092773, "genuineness": 3.8044304847717285, "identity": 0.6017279624938965, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben di sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.25, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f6814d2e97cdded85876cfe4a5204ae40b52dedce65652cc26966768abae3697.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "f6b8d409204a98085f189350637e088566a3eb97caf174298d6c1bc9b93b6489", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3359af459fd706b9da029324abf7bcd73c5865bdb38c3ba73682d325dc8d67a9", "generation_seconds_batch": 22.118898217915557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.596663236618042, "target_z": 3.718750158330894, "ce": 5.601652145385742, "genuineness": 3.7416701316833496, "identity": 0.42009228467941284, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f6b8d409204a98085f189350637e088566a3eb97caf174298d6c1bc9b93b6489.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": "f7008f7a4c68cbc63aa9e345ebabffc2ac39caf1df3bb44ce04aed2e139f5af7", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4d25c0c8e863cacdd94ac69ac63fabf076a4258131feec900b3dd39637dc283d", "generation_seconds_batch": 21.230915053980425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6540138721466064, "target_z": 3.812499975641401, "ce": 5.720792293548584, "genuineness": 3.9927117824554443, "identity": 0.3419497311115265, "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_Fear/f7008f7a4c68cbc63aa9e345ebabffc2ac39caf1df3bb44ce04aed2e139f5af7.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "f72d5505329cd037ead40879157d12f0baffb9fdbae40c796cfb9bd2ca5c7151", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "613a1b7ae3735580bd27bb93483678198383df8850dc1cfb81fbdaefdb8312af", "generation_seconds_batch": 22.729310101014562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.56434965133667, "target_z": 2.0312499391035024, "ce": 6.006728172302246, "genuineness": 4.281409740447998, "identity": 0.5086871981620789, "hypothesis": "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_Fear/f72d5505329cd037ead40879157d12f0baffb9fdbae40c796cfb9bd2ca5c7151.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "f73757b75d17224c442cc40dbef15fb09475504a3827cbf7f4f5b76c5f1a4fc9", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7b12604faf8939975ea3051b43c0d344116b3551bdaafded003a8fc85ca884cd", "generation_seconds_batch": 16.14694984909147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01518547534942627, "target_z": -0.5507812484775876, "ce": 6.348263263702393, "genuineness": 4.557555198669434, "identity": 0.5783575773239136, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f73757b75d17224c442cc40dbef15fb09475504a3827cbf7f4f5b76c5f1a4fc9.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": "f77629f2a2b4e5daaa21b94b4de22b7ace94f0078ca7d0d84306286e5b5605c5", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "04e6e36ec7b6c45ece70886d19db0539ca92d4b0638080b72359c216773f4edf", "generation_seconds_batch": 15.532252046046779, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9334914684295654, "target_z": 1.0, "ce": 5.974957466125488, "genuineness": 4.250029563903809, "identity": 0.5944496393203735, "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_Fear/f77629f2a2b4e5daaa21b94b4de22b7ace94f0078ca7d0d84306286e5b5605c5.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "f79f337c5483f0ef5ded45167fb31ad96216184429d3de585e132f540ffb1c5e", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "be8ccad61f731d1c79cb568edd9c7c8d1846ce52f4f3a55b1b35d6ce631523db", "generation_seconds_batch": 15.745606953045353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02065873146057129, "target_z": -0.49218751522412446, "ce": 6.117925643920898, "genuineness": 4.532451152801514, "identity": 0.7355072498321533, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f79f337c5483f0ef5ded45167fb31ad96216184429d3de585e132f540ffb1c5e.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "5ea2c6148ad65dadd2cee73bca9c7d32df6d220113e78309b2f463f77fb194f3", "generation_seconds_batch": 16.116828263970092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0039314329624176025, "target_z": -0.5195312606568872, "ce": 6.157639026641846, "genuineness": 4.607763767242432, "identity": 0.6508986949920654, "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_Fear/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "f816c6cb0cff95e2d016a6f109eb5cc3aaad3035dce33db8c3cd41cab592e56c", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "30f78100385d341a32f77611e1f6dac0b8e5f23cdc7ba9361dd1c9fab9a33977", "generation_seconds_batch": 14.470269965007901, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027827590703964233, "target_z": -0.4804687393431129, "ce": 6.109982967376709, "genuineness": 4.7332844734191895, "identity": 0.7798058390617371, "hypothesis": "He encontrado la cajita. Estaba junto estaba junto a 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_Fear/f816c6cb0cff95e2d016a6f109eb5cc3aaad3035dce33db8c3cd41cab592e56c.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "f86e7ae19718eb8896a8de4382fc55842f6a2686af1470737b13e3af12346bfb", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3855cca68a137028eb6b4a29b0984c3a92c7712f6d9f4317ef1e281e3868d36a", "generation_seconds_batch": 20.843444645986892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023048341274261475, "target_z": -0.48828127283618666, "ce": 5.990842819213867, "genuineness": 4.532451152801514, "identity": 0.6719412803649902, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f86e7ae19718eb8896a8de4382fc55842f6a2686af1470737b13e3af12346bfb.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "f86ebb2d2be06d2bc9fedcfea66e5a822ad4ea5e43e3673ff9505242e31c8b29", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ef7d3a5827f907672f4097c25c5bd97dd30971b68ff78f1700775fa937243189", "generation_seconds_batch": 19.83656606695149, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1151021718978882, "target_z": 1.2968750060896497, "ce": 4.810611724853516, "genuineness": 3.8044304847717285, "identity": 0.4810168743133545, "hypothesis": "Ich habe die kleine Schacht gefunden. Sie standen neben dem alten Feldgönn, gemeinsam hineinschauen!", "wer": 0.3125, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f86ebb2d2be06d2bc9fedcfea66e5a822ad4ea5e43e3673ff9505242e31c8b29.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_Fear", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": "57b2ae7984351bd7359f68a23b1424c8825b3e4a251edaba8d552d215a0486a7", "generation_seconds_batch": 16.755568448919803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021853536367416382, "target_z": -0.49023439403015556, "ce": 6.292664527893066, "genuineness": 4.607763767242432, "identity": 0.5300527811050415, "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_Fear/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "f8efd503cf8532a5c28dfbb73f9850834943d573d8b0d058c83f5bc57a7a22e4", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5465e3a54ae78673fb11272dd1a4b86fa884e410d7a65ed70c2c7d1a98cc9b43", "generation_seconds_batch": 14.941641364945099, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1510536670684814, "target_z": 4.624999951282802, "ce": 6.1020402908325195, "genuineness": 3.71028995513916, "identity": 0.5366899967193604, "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": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f8efd503cf8532a5c28dfbb73f9850834943d573d8b0d058c83f5bc57a7a22e4.mp3" }, { "id": "emo_Fear-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar 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_Fear-nl-0", "key": "f8f0d2337d513bbbd2a3ca9f56c6189b1ae4a36d98eb24b6c2cec85ce70bd113", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] De deur staat nog open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6ecd5c2501420d06b2127e0701f8a579aefe452b601168d8b620258d0e50ec4e", "generation_seconds_batch": 16.825836039031856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21839934587478638, "target_z": -0.16894529994009733, "ce": 5.871703147888184, "genuineness": 4.243753433227539, "identity": 0.5666795969009399, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f8f0d2337d513bbbd2a3ca9f56c6189b1ae4a36d98eb24b6c2cec85ce70bd113.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "f9a5723edb36c5cd908bab9dcee55d8d0c36e921abb778a674367162852ef31d", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "48ef08e93b5384e33cb7d8b4697be45bc00f0877de544fee91947116de2ec1b1", "generation_seconds_batch": 20.496070613036864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9216506481170654, "target_z": 4.2499999025656034, "ce": 6.165581703186035, "genuineness": 3.873466968536377, "identity": 0.6895939111709595, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/f9a5723edb36c5cd908bab9dcee55d8d0c36e921abb778a674367162852ef31d.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "fa95b2d91ab925015f1744d17a19971bc784aeafe205b8dcde7e43486828fa8a", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "68b0c9407e2f1a99fcf0ec563324f6f0b1fda269735fd9c723d52c3e93c78bb2", "generation_seconds_batch": 15.515750481979921, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04574969410896301, "target_z": -0.4511718727163813, "ce": 6.356205940246582, "genuineness": 4.65797233581543, "identity": 0.6402833461761475, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/fa95b2d91ab925015f1744d17a19971bc784aeafe205b8dcde7e43486828fa8a.mp3" }, { "id": "emo_Fear-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos 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_Fear-es-1", "key": "fb5aed74622fd6727a636e74ecdcdf8d7a20a3fe82a4e925d52f97151b0d8679", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a5909e03f24bd67cbdaab35c40b16364480a40ae25bce88a7355d1987432784b", "generation_seconds_batch": 20.452486629015766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021853536367416382, "target_z": -0.49023439403015556, "ce": 6.197352409362793, "genuineness": 4.896461486816406, "identity": 0.6387070417404175, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/fb5aed74622fd6727a636e74ecdcdf8d7a20a3fe82a4e925d52f97151b0d8679.mp3" }, { "id": "emo_Fear-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. 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_Fear-de-1", "key": "fb8a5e1cfab8302d267202672b0a6516284553cabaca08b575b52b633cb1b344", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5a297d97557a0e0f2c2e535bfcf2dfcece51aaa321d0d0f87534b2de5fa5c04e", "generation_seconds_batch": 21.495653947000392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0039314329624176025, "target_z": -0.5195312606568872, "ce": 6.268836498260498, "genuineness": 4.444586753845215, "identity": 0.565255880355835, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/fb8a5e1cfab8302d267202672b0a6516284553cabaca08b575b52b633cb1b344.mp3" }, { "id": "emo_Fear-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen 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_Fear-nl-1", "key": "fd124edf182d0562528b22512a82d086cba5d2e328adbb18e83d8204ff2835c7", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Het stond naast het oude raam.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "53982d469559c9cc45efeaaef6042adc8b8c83585a3e5d0ffe6191ac5ffdc17d", "generation_seconds_batch": 21.857322057010606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1187400817871094, "target_z": 2.93749973205541, "ce": 5.2918877601623535, "genuineness": 3.528284788131714, "identity": 0.279796302318573, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/fd124edf182d0562528b22512a82d086cba5d2e328adbb18e83d8204ff2835c7.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": "fd493b8e33902546cf64117ae383783f283aad02f439e979f7fe8e7cca8bb55f", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6c695a82e6b9d125c51fe0742114632dbdebcccbe5f98828002f56caa0c3e13d", "generation_seconds_batch": 16.23187083809171, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5871047973632812, "target_z": 3.703125188779143, "ce": 5.629451274871826, "genuineness": 3.7165660858154297, "identity": 0.5814074277877808, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. ¡Te esperaré al otro lado!", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/fd493b8e33902546cf64117ae383783f283aad02f439e979f7fe8e7cca8bb55f.mp3" }, { "id": "emo_Fear-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble 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_Fear-fr-1", "key": "fdf1acf0efe94208a68d247c0a24bdbf08ddc081d9cd5652f1f42e738f362cd7", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9cb942f024405897dc4e3258515e76989b3de6c265595c98eee43cb905f808e2", "generation_seconds_batch": 21.62508882698603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06725621223449707, "target_z": -0.4160156425077431, "ce": 6.006728172302246, "genuineness": 4.362998008728027, "identity": 0.7274045944213867, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/fdf1acf0efe94208a68d247c0a24bdbf08ddc081d9cd5652f1f42e738f362cd7.mp3" }, { "id": "emo_Fear-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi 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_Fear-fr-0", "key": "fdfc6d02a0a49a6127c7536d9c69fe4c6b419222b0befff82dc580e2b9454f6e", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7d017b284049ebd55f72ac1020f7632e61e07d6891705c00236503ca467cd913", "generation_seconds_batch": 21.89527939702384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04933410882949829, "target_z": -0.4453125091344747, "ce": 6.046441555023193, "genuineness": 4.532451152801514, "identity": 0.7828071713447571, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/fdfc6d02a0a49a6127c7536d9c69fe4c6b419222b0befff82dc580e2b9454f6e.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": "ff4bc2ad6c7e24a036f743c1a28bc588bace0ce3ca26911c06c610acf2e43e03", "bucket": "emo_Fear", "phase": "heldout", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a8340de3c71cd8a16c82407bee3eea646e833569220846d53d22a300b9327065", "generation_seconds_batch": 15.68596842396073, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6981680393218994, "target_z": 2.2499999025656034, "ce": 5.526196479797363, "genuineness": 3.9927117824554443, "identity": 0.5706014633178711, "hypothesis": "Ton message est arrivé. Après mon départ, je l'ai relu. J'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ff4bc2ad6c7e24a036f743c1a28bc588bace0ce3ca26911c06c610acf2e43e03.mp3" }, { "id": "emo_Fear-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me 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_Fear-en-0", "key": "ffbf8b43fa25bfc2218b3718cbeffccafac49a02f78216faf6a1ac76f8de1d45", "bucket": "emo_Fear", "phase": "wording", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] The door is still open.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] I put your coat on the chair.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "84618efcc63a1c91cbeb71983698d6033eaf1cef76b8b997577806ce5e317473", "generation_seconds_batch": 16.259603237966076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003237396478652954, "target_z": -0.5312499878207004, "ce": 6.213237762451172, "genuineness": 4.068024158477783, "identity": 0.24035046994686127, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Fear/ffbf8b43fa25bfc2218b3718cbeffccafac49a02f78216faf6a1ac76f8de1d45.mp3" }, { "id": "emo_Fear-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. 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_Fear-es-0", "key": "ffe45f6238e7913c176e369ea1a338a289f876615441d63ddb01d407c5d1acee", "bucket": "emo_Fear", "phase": "grid", "candidate": "manual-e2b016e601f8", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Channel the panic as a physical constriction in the throat, forcing the vocal output to feel strained and barely contained throughout the entire delivery.\nSCRIPT:\n(Start with a shallow, rapid intake of breath that immediately tightens the vocal cords.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain that constricted feeling, allowing only fragmented, urgent bursts of sound.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(End with the sound catching in the throat, a desperate, high-tension release.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d7d119f6d925ee2b87d841ab5f5d53dc1917efb8ebcce8f8f48c8e71abd41fd8", "generation_seconds_batch": 19.324236282031052, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.067309856414795, "target_z": 1.2187499634621013, "ce": 5.863759994506836, "genuineness": 4.231201171875, "identity": 0.5162758827209473, "hypothesis": "La puerta sigue. 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_Fear/ffe45f6238e7913c176e369ea1a338a289f876615441d63ddb01d407c5d1acee.mp3" }, { "key": "original-emo_Fear-de-0-seed1701-scale0.0", "bucket": "emo_Fear", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "d35dab0df4d863a8947da4279375ca0c625241dc8392c7cb4764d9e263e56588", "task_id": "emo_Fear-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.0481393039226532, "target_z": -0.4472656303284436, "ce": 6.229123115539551, "genuineness": 4.796044826507568, "identity": 0.6347805261611938, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/de/12c83b271e1112a14e6b4bd9.mp3" }, { "key": "original-emo_Fear-de-0-seed1701-scale0.5", "bucket": "emo_Fear", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "171bd9b6d331feab845488d78db0a3de539f877e66190c19e070338388eaaeeb", "task_id": "emo_Fear-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.061282187700271606, "target_z": -0.4257812484775876, "ce": 6.1020402908325195, "genuineness": 4.494794845581055, "identity": 0.6550287008285522, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/de/1e7bd27c3696967fb78c035f.mp3" }, { "key": "original-emo_Fear-de-0-seed1701-scale0.75", "bucket": "emo_Fear", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "41b55f6214ba6ae37a7929ac99c528016e267ca8276d252c04ca154fcdc14025", "task_id": "emo_Fear-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.04336008429527283, "target_z": -0.4550781151043191, "ce": 6.197352409362793, "genuineness": 4.469690799713135, "identity": 0.6888556480407715, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/de/367bb29edda3c8924cccd69c.mp3" }, { "key": "original-emo_Fear-de-0-seed1701-scale1.0", "bucket": "emo_Fear", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "9a7de9b423698e909a53abbb097dc9c2cf0952b6b0664eab5060cd55358cf2a5", "task_id": "emo_Fear-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.02663278579711914, "target_z": -0.4824218605370818, "ce": 6.086154937744141, "genuineness": 4.444586753845215, "identity": 0.5060653686523438, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/de/0fd417c972d92c1f9ae85950.mp3" }, { "key": "original-emo_Fear-de-0-seed1702-scale0.0", "bucket": "emo_Fear", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "833884726bc51ab3202e705e32bef668a286ff0d7daa61151a7bfeabc9904386", "task_id": "emo_Fear-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.09354197978973389, "target_z": -0.3730468788060311, "ce": 6.24500846862793, "genuineness": 4.532451152801514, "identity": 0.6532990336418152, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/de/801855557461ce9c63381b33.mp3" }, { "key": "original-emo_Fear-de-0-seed1702-scale0.5", "bucket": "emo_Fear", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "3b9c76de0bd0be9132ff9bd61ad30da9930e291d9297688c3cddb2302ddd7082", "task_id": "emo_Fear-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.08398352563381195, "target_z": -0.3886718727163813, "ce": 6.213237762451172, "genuineness": 4.607763767242432, "identity": 0.44957104325294495, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/de/6728eef21f9515054da61365.mp3" }, { "key": "original-emo_Fear-de-0-seed1702-scale0.75", "bucket": "emo_Fear", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "5b45792bec7e312fb5572f776a8f124f221927c4f2a54fe43c9bd53ef359d1aa", "task_id": "emo_Fear-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.06367179751396179, "target_z": -0.4218750060896498, "ce": 6.181467056274414, "genuineness": 4.632867813110352, "identity": 0.4074232578277588, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/de/d1bd8177114142a6afa49e61.mp3" }, { "key": "original-emo_Fear-de-0-seed1702-scale1.0", "bucket": "emo_Fear", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "d487ac38f1a4fd5b4181e9a1a34cc8c0141f9b0f9bc03377e5360e7e71084458", "task_id": "emo_Fear-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.07203544676303864, "target_z": -0.40820313337326847, "ce": 6.229123115539551, "genuineness": 4.375550270080566, "identity": 0.5868048667907715, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/de/64cbb6afaefaad95d7b60b0d.mp3" }, { "key": "original-emo_Fear-de-1-seed1701-scale0.0", "bucket": "emo_Fear", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "00e27210252522806d0f9f8240374e5fa8a2a4300085c9da3c00a1b900fa110c", "task_id": "emo_Fear-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.015879511833190918, "target_z": -0.5, "ce": 6.403861999511719, "genuineness": 4.457139015197754, "identity": 0.5843411684036255, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/de/d327f44df0d5e4b5a0458626.mp3" }, { "key": "original-emo_Fear-de-1-seed1701-scale0.5", "bucket": "emo_Fear", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "fca986cbcdc96dee516f75c6c05fc159e9f13e0b78fdab5f2d1caf1f2f39e705", "task_id": "emo_Fear-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": -0.0008477866649627686, "target_z": -0.5273437454327626, "ce": 6.41180419921875, "genuineness": 4.469690799713135, "identity": 0.5599363446235657, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/de/a2eba498b0c49e707c318cc8.mp3" }, { "key": "original-emo_Fear-de-1-seed1701-scale0.75", "bucket": "emo_Fear", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "d16453ef448ac83ef670b84afccaa929ac584a985866356629c7eac68183161e", "task_id": "emo_Fear-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.03858083486557007, "target_z": -0.4628906485973929, "ce": 6.38003396987915, "genuineness": 4.400654315948486, "identity": 0.5321459770202637, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/de/64ffe164b797dc009d3cb7b5.mp3" }, { "key": "original-emo_Fear-de-1-seed1701-scale1.0", "bucket": "emo_Fear", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "b1686635f49240949462a4705e3735b9d1b2bd2c71933ef8bc93c8e0649730b9", "task_id": "emo_Fear-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.03499642014503479, "target_z": -0.46875001217929957, "ce": 6.419747352600098, "genuineness": 4.218649387359619, "identity": 0.5558608174324036, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/de/1e956a18a3b9a45bd9aa425d.mp3" }, { "key": "original-emo_Fear-de-1-seed1702-scale0.0", "bucket": "emo_Fear", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "58731c327891e20f9f209432e79f4ff41f0af9cc56a31743be0dbc1ad7d827fc", "task_id": "emo_Fear-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.02663278579711914, "target_z": -0.4824218605370818, "ce": 6.332377910614014, "genuineness": 4.557555198669434, "identity": 0.6658584475517273, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/de/803c9eb51df263efd5cd1de0.mp3" }, { "key": "original-emo_Fear-de-1-seed1702-scale0.5", "bucket": "emo_Fear", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "15d521243a229c1416e096f557a46e3e60ee4df9f59973c6f70c1c8bfcfbbeb8", "task_id": "emo_Fear-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.018269121646881104, "target_z": -0.4960937576120622, "ce": 6.340320587158203, "genuineness": 4.268857479095459, "identity": 0.4550379514694214, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/de/6f967ee24f1a641198edfdaa.mp3" }, { "key": "original-emo_Fear-de-1-seed1702-scale0.75", "bucket": "emo_Fear", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "91ce5d6522c2f0a9550776d78e549a2f48bfcb2e69f1cba6a38c09965f7d39fe", "task_id": "emo_Fear-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": -0.01518547534942627, "target_z": -0.5507812484775876, "ce": 6.332377910614014, "genuineness": 4.344170093536377, "identity": 0.6956007480621338, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/de/d6c5a26b0128765f86c2cf3f.mp3" }, { "key": "original-emo_Fear-de-1-seed1702-scale1.0", "bucket": "emo_Fear", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "1db6cdb50853e87aab5e6d619601e5c09f453109ef933142ea823981e3bf8327", "task_id": "emo_Fear-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.02663278579711914, "target_z": -0.4824218605370818, "ce": 6.419747352600098, "genuineness": 4.507347106933594, "identity": 0.6564646363258362, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/de/21fbd3714e356095cb7a7f0a.mp3" }, { "key": "original-emo_Fear-en-0-seed1701-scale0.0", "bucket": "emo_Fear", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "34b80d5c0c6cf08406efc42b3130d6ca4e79731a73b47c0f64998d218145179e", "task_id": "emo_Fear-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.006321042776107788, "target_z": -0.5156250182689494, "ce": 6.300607204437256, "genuineness": 4.369274139404297, "identity": 0.26281917095184326, "hypothesis": "The 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_Fear/en/f29e37d936317929d336c605.mp3" }, { "key": "original-emo_Fear-en-0-seed1701-scale0.5", "bucket": "emo_Fear", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "b59a71a7efa36460f09b8a84680444ce66dac1ae9535954662f01508ff46b054", "task_id": "emo_Fear-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": -0.008016645908355713, "target_z": -0.5390625213137742, "ce": 6.2767791748046875, "genuineness": 3.9801597595214844, "identity": 0.45040297508239746, "hypothesis": "The 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_Fear/en/87ed278821536d7b24d5b289.mp3" }, { "key": "original-emo_Fear-en-0-seed1701-scale0.75", "bucket": "emo_Fear", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "98207cc5c27e5ace3fda524d4eacc00a34f56e1814f833b1a05fa9d0f281b8a9", "task_id": "emo_Fear-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": -0.003237396478652954, "target_z": -0.5312499878207004, "ce": 6.086154937744141, "genuineness": 4.005263805389404, "identity": 0.5261510610580444, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/en/5c544964a93335b380d9d48c.mp3" }, { "key": "original-emo_Fear-en-0-seed1701-scale1.0", "bucket": "emo_Fear", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "a75e6cc8c578b23794fbd4d60c315449f8f1f709c69207c6a8f4e7673ace3277", "task_id": "emo_Fear-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": -0.017575085163116455, "target_z": -0.5546874908655254, "ce": 6.1894097328186035, "genuineness": 4.13078498840332, "identity": 0.36745622754096985, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/en/beca6e435772b19a43d24827.mp3" }, { "key": "original-emo_Fear-en-0-seed1702-scale0.0", "bucket": "emo_Fear", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "4593435dec7457d4da33ec19ccadced67c321164e7741e01c7559649e608661e", "task_id": "emo_Fear-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": -0.00562700629234314, "target_z": -0.5351562302086382, "ce": 6.054384231567383, "genuineness": 3.860914945602417, "identity": 0.35707443952560425, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/en/5a33f5fec8b2ac52ad7fb4ce.mp3" }, { "key": "original-emo_Fear-en-0-seed1702-scale0.5", "bucket": "emo_Fear", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "2eda3b499ce8909e550f58ed6ca4a3e428984f8ac5ae7615f9985cab8e033eb4", "task_id": "emo_Fear-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.015879511833190918, "target_z": -0.5, "ce": 6.24500846862793, "genuineness": 3.986435890197754, "identity": 0.3874278962612152, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/en/5833d858164cc784f6899788.mp3" }, { "key": "original-emo_Fear-en-0-seed1702-scale0.75", "bucket": "emo_Fear", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.75, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "4a26cf83fe1f509978c92d735aee237843fec566e1b3e2e1bc785cb1beec7225", "task_id": "emo_Fear-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.008710682392120361, "target_z": -0.5117187271638133, "ce": 6.1020402908325195, "genuineness": 4.105680465698242, "identity": 0.4798573851585388, "hypothesis": "The 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_Fear/en/f88b7486835547ed96110264.mp3" }, { "key": "original-emo_Fear-en-0-seed1702-scale1.0", "bucket": "emo_Fear", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "99a3617ad1d59d784ca2eed3fd112dff4b1c924e82c6fb0442e15b429d12fdee", "task_id": "emo_Fear-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.001541823148727417, "target_z": -0.5234375030448248, "ce": 6.086154937744141, "genuineness": 4.074300289154053, "identity": 0.2333751618862152, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/en/d038a1d6fc91f761e6e8bbc7.mp3" }, { "key": "original-emo_Fear-en-1-seed1701-scale0.0", "bucket": "emo_Fear", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "c78b4af6f9ebd5c377a02a7e3c2c7f4b4f7aa0478427aeafa49ad2066b94a94e", "task_id": "emo_Fear-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.015879511833190918, "target_z": -0.5, "ce": 6.292664527893066, "genuineness": 4.3127899169921875, "identity": 0.31862500309944153, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/en/f7d0a2d14402ec00798febd3.mp3" }, { "key": "original-emo_Fear-en-1-seed1701-scale0.5", "bucket": "emo_Fear", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "e9fc873b5ade804ddf064951e952cab425d2c1a5c3a5356130953f8198904d5b", "task_id": "emo_Fear-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.02065873146057129, "target_z": -0.49218751522412446, "ce": 6.300607204437256, "genuineness": 4.432034492492676, "identity": 0.42830222845077515, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/en/4eb678d965740ad8dab13bcd.mp3" }, { "key": "original-emo_Fear-en-1-seed1701-scale0.75", "bucket": "emo_Fear", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "559104850535c138f71fb317480aaf075d3503e1b4ee666b9a7f834351c1e9c7", "task_id": "emo_Fear-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.018269121646881104, "target_z": -0.4960937576120622, "ce": 6.300607204437256, "genuineness": 4.369274139404297, "identity": 0.4522286057472229, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/en/1234c88a50ebbd4476d61dfc.mp3" }, { "key": "original-emo_Fear-en-1-seed1701-scale1.0", "bucket": "emo_Fear", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "365df1a039fa313615cdf8ad742c9b778d098fe0d57489e6816db1324eae75f6", "task_id": "emo_Fear-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.021853536367416382, "target_z": -0.49023439403015556, "ce": 6.284721851348877, "genuineness": 4.344170093536377, "identity": 0.4147648513317108, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/en/4aea9796af8c1b505b70f4c8.mp3" }, { "key": "original-emo_Fear-en-1-seed1702-scale0.0", "bucket": "emo_Fear", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "f4638494dce04be425aae3a459f475ffe9a41d63eaf9a1696943edc122c90ca6", "task_id": "emo_Fear-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.008710682392120361, "target_z": -0.5117187271638133, "ce": 6.332377910614014, "genuineness": 4.287685871124268, "identity": 0.36881178617477417, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/en/9c1fe06b7f2d96b703ae9ab5.mp3" }, { "key": "original-emo_Fear-en-1-seed1702-scale0.5", "bucket": "emo_Fear", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "b050fb78a504022504449f6407e42be7d794d985fbc4a177b436e499a2a93b45", "task_id": "emo_Fear-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.0039314329624176025, "target_z": -0.5195312606568872, "ce": 6.229123115539551, "genuineness": 4.369274139404297, "identity": 0.513702929019928, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/en/ae1552931dd481fc1169f63f.mp3" }, { "key": "original-emo_Fear-en-1-seed1702-scale0.75", "bucket": "emo_Fear", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.75, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "2d1d1d27d73080b0945bae5c2cdc3c6a623090e4f91157830803b7cf43bacbdc", "task_id": "emo_Fear-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.008710682392120361, "target_z": -0.5117187271638133, "ce": 6.3641486167907715, "genuineness": 4.337893962860107, "identity": 0.5344716906547546, "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_Fear/en/a7217fd5746701e5d92693d7.mp3" }, { "key": "original-emo_Fear-en-1-seed1702-scale1.0", "bucket": "emo_Fear", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "77d733f71d978e62a389ebe7e1a64f7e58bea2b1a04c35be9a3c8da414f16dfa", "task_id": "emo_Fear-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": -0.012795865535736084, "target_z": -0.5468750060896498, "ce": 6.1894097328186035, "genuineness": 4.21237325668335, "identity": 0.3753975033760071, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/en/f4f7efed0144f2c650568841.mp3" }, { "key": "original-emo_Fear-es-0-seed1701-scale0.0", "bucket": "emo_Fear", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "33a33ab44c606452de1bc79934a392f705e0d672f477155681a2ee2203a0f24d", "task_id": "emo_Fear-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.10310043394565582, "target_z": -0.3574218848956809, "ce": 6.062326908111572, "genuineness": 4.482243061065674, "identity": 0.7478245496749878, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/es/98017091704764b3d9b4c2e8.mp3" }, { "key": "original-emo_Fear-es-0-seed1701-scale0.5", "bucket": "emo_Fear", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "58f62ef5ac7780bfeb84d89b130beae3b0f718ff4eb0f73546a47fcde2dc9af0", "task_id": "emo_Fear-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.09951601922512054, "target_z": -0.3632812484775876, "ce": 6.046441555023193, "genuineness": 4.3881025314331055, "identity": 0.723715603351593, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/es/e84b8f6b268ec6eafcb05fe3.mp3" }, { "key": "original-emo_Fear-es-0-seed1701-scale0.75", "bucket": "emo_Fear", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "7b9360ee5a6806a343e2f9fd730c29320809449a65e80a148cff0f2589206e4a", "task_id": "emo_Fear-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.08637313544750214, "target_z": -0.3847656303284436, "ce": 5.95112943649292, "genuineness": 4.256305694580078, "identity": 0.5023594498634338, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/es/7eca5921e4ca79c6211bb9e3.mp3" }, { "key": "original-emo_Fear-es-0-seed1701-scale1.0", "bucket": "emo_Fear", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "71d19f2a8f4cf8e2947443d96ed9b7146fcbc571826b025c561f85f392a081f5", "task_id": "emo_Fear-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.09832121431827545, "target_z": -0.3652343696715564, "ce": 5.982900142669678, "genuineness": 4.030367851257324, "identity": 0.5376332998275757, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/es/2a42e7c3f4d4721443f6c38f.mp3" }, { "key": "original-emo_Fear-es-0-seed1702-scale0.0", "bucket": "emo_Fear", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "ec833429fe773d923b5ac2bdbcafc093d87e212c6905e2912bdd3dce0c8c1d77", "task_id": "emo_Fear-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.12341216206550598, "target_z": -0.3242187515224124, "ce": 5.879645347595215, "genuineness": 4.344170093536377, "identity": 0.5279291272163391, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/es/dfc7a7f96c5d5e5724d29d40.mp3" }, { "key": "original-emo_Fear-es-0-seed1702-scale0.5", "bucket": "emo_Fear", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "f69071f7bb8d7d1d7a8859cc42349f58e736d3be071e6c246444347d28e7afd4", "task_id": "emo_Fear-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.09712640941143036, "target_z": -0.3671874908655253, "ce": 6.24500846862793, "genuineness": 4.7081804275512695, "identity": 0.5046660304069519, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/es/c2011bca5cd8a0ef504d17f6.mp3" }, { "key": "original-emo_Fear-es-0-seed1702-scale0.75", "bucket": "emo_Fear", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "df83c8e43ff651d7282cc358ea4951f31b4451dc227fee1e706ff895a84675da", "task_id": "emo_Fear-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.05889257788658142, "target_z": -0.4296874908655253, "ce": 6.078212261199951, "genuineness": 3.6663577556610107, "identity": 0.5687424540519714, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/es/7a521096de84e7dd0229873d.mp3" }, { "key": "original-emo_Fear-es-0-seed1702-scale1.0", "bucket": "emo_Fear", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "4323da976594ccb61bda000e1699dc853b56cf3b58f184e2444f489e74e253e3", "task_id": "emo_Fear-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.056502968072891235, "target_z": -0.4335937332534631, "ce": 5.935244083404541, "genuineness": 4.017816066741943, "identity": 0.5323199033737183, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/es/66cb68e659c1774c5f923138.mp3" }, { "key": "original-emo_Fear-es-1-seed1701-scale0.0", "bucket": "emo_Fear", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "146b2f3faa8b8ab6ec0d2b053337d5301f52d57a5548598f97e3147bcfc64b0f", "task_id": "emo_Fear-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.03141200542449951, "target_z": -0.4746093757612062, "ce": 6.054384231567383, "genuineness": 4.444586753845215, "identity": 0.5174858570098877, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/es/e84bc5869ce8fe6d365fbdf2.mp3" }, { "key": "original-emo_Fear-es-1-seed1701-scale0.5", "bucket": "emo_Fear", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "c5f851f8f4e54efd3f0be09fbd9a4a6c13f73233f5b360d8685b7f8455f1808d", "task_id": "emo_Fear-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.03858083486557007, "target_z": -0.4628906485973929, "ce": 6.141753673553467, "genuineness": 4.6203155517578125, "identity": 0.6708419919013977, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/es/2f24d6b59ded2c7a562407bc.mp3" }, { "key": "original-emo_Fear-es-1-seed1701-scale0.75", "bucket": "emo_Fear", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "c8b9226b8067cd4366dc15a0ff643a3feedc2fb4ce450193ec23d188ff25e081", "task_id": "emo_Fear-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.04933410882949829, "target_z": -0.4453125091344747, "ce": 6.252951145172119, "genuineness": 4.68307638168335, "identity": 0.5429399013519287, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/es/0a840eb742b67c36c0a9fce3.mp3" }, { "key": "original-emo_Fear-es-1-seed1701-scale1.0", "bucket": "emo_Fear", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "41d69ab50d6334e35b916825cb4fae4b297c96825d77ef62162076b8602c3be1", "task_id": "emo_Fear-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.05172371864318848, "target_z": -0.4414062667465369, "ce": 6.046441555023193, "genuineness": 4.65797233581543, "identity": 0.3788544833660126, "hypothesis": "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_Fear/es/f6c2c4c2c5cd7fab521816b6.mp3" }, { "key": "original-emo_Fear-es-1-seed1702-scale0.0", "bucket": "emo_Fear", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "9b5f1a11c6c6697e486763ffbc4869141ecda50cdcec2a1329660b55dad69565", "task_id": "emo_Fear-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.04933410882949829, "target_z": -0.4453125091344747, "ce": 6.046441555023193, "genuineness": 4.68307638168335, "identity": 0.5639294981956482, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/es/924c3921d3046e8fe1f15e18.mp3" }, { "key": "original-emo_Fear-es-1-seed1702-scale0.5", "bucket": "emo_Fear", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "1b7fd3105836837a80e975fa49244b6b9c77e6d995d43ba04d8bbe1791718476", "task_id": "emo_Fear-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.050528913736343384, "target_z": -0.4433593879405058, "ce": 6.125868320465088, "genuineness": 4.6956281661987305, "identity": 0.5912987589836121, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/es/d0cb5c954230bc8b36c75e3b.mp3" }, { "key": "original-emo_Fear-es-1-seed1702-scale0.75", "bucket": "emo_Fear", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "80c5fe9c7cecb92f7fa0775bc75a05ee8d595e3d632912292fedc8da8b5b1c8b", "task_id": "emo_Fear-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.04455488920211792, "target_z": -0.4531249939103502, "ce": 6.086154937744141, "genuineness": 4.494794845581055, "identity": 0.6194959878921509, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/es/d2ff9da9e72102ef53bd265c.mp3" }, { "key": "original-emo_Fear-es-1-seed1702-scale1.0", "bucket": "emo_Fear", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 1.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "0740e91cc34ea9155e0c13bb47b1e9a923fd661bcab01192629099db6db333f3", "task_id": "emo_Fear-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.05291852355003357, "target_z": -0.439453145552568, "ce": 6.181467056274414, "genuineness": 4.356721878051758, "identity": 0.5794345140457153, "hypothesis": "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_Fear/es/f20bb4981ea78a820c0c53ee.mp3" }, { "key": "original-emo_Fear-fr-0-seed1701-scale0.0", "bucket": "emo_Fear", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "295160005af36a98ad3f0f5289246ac29eb054172a968dbeb71beccb45f29eaf", "task_id": "emo_Fear-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.056502968072891235, "target_z": -0.4335937332534631, "ce": 5.990842819213867, "genuineness": 4.406930446624756, "identity": 0.6696234941482544, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/fr/46a033fc434fc37c896525f1.mp3" }, { "key": "original-emo_Fear-fr-0-seed1701-scale0.5", "bucket": "emo_Fear", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "58195b8607eb17013989d500381b6d5dbd7ad4523319e6d61562b3bb89f90bca", "task_id": "emo_Fear-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.07084065675735474, "target_z": -0.41015623020863823, "ce": 6.022613525390625, "genuineness": 4.344170093536377, "identity": 0.7617517709732056, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/fr/8c300f6d9856d7b2ad94bf2f.mp3" }, { "key": "original-emo_Fear-fr-0-seed1701-scale0.75", "bucket": "emo_Fear", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "3f2705204b8f3ee102167e000c2259ebf892eb34e299d0f76a98a28b34e0cbe1", "task_id": "emo_Fear-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.05530816316604614, "target_z": -0.435546854447432, "ce": 6.165581703186035, "genuineness": 4.419482707977295, "identity": 0.6240725517272949, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/fr/15243cd4059c7784c37217d4.mp3" }, { "key": "original-emo_Fear-fr-0-seed1701-scale1.0", "bucket": "emo_Fear", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "918ec370d91ae4d1d6368178b20e2777ee1cd389449a63506d3d60162184a295", "task_id": "emo_Fear-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.01707431674003601, "target_z": -0.4980468788060311, "ce": 6.078212261199951, "genuineness": 4.65797233581543, "identity": 0.7686789631843567, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/fr/170e147a00314e1d6c2752c8.mp3" }, { "key": "original-emo_Fear-fr-0-seed1702-scale0.0", "bucket": "emo_Fear", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "982b8a93e67befdb947dac5f6c03d1231f4f93c9b12f58fd3dd6d714b5726ed8", "task_id": "emo_Fear-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.05291852355003357, "target_z": -0.439453145552568, "ce": 5.919358730316162, "genuineness": 4.344170093536377, "identity": 0.6022547483444214, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/fr/e1b4990a863c98bdcc41cc75.mp3" }, { "key": "original-emo_Fear-fr-0-seed1702-scale0.5", "bucket": "emo_Fear", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "9b53e2863d89d0546ffed447b3aac75ae8022201614bb2c27c274c54d9c1a223", "task_id": "emo_Fear-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.06964585185050964, "target_z": -0.4121093514026071, "ce": 6.062326908111572, "genuineness": 4.432034492492676, "identity": 0.6565498113632202, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/fr/37e62827a4463747aa1b7863.mp3" }, { "key": "original-emo_Fear-fr-0-seed1702-scale0.75", "bucket": "emo_Fear", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "037a5a363845d54641f6cea44e881b45f223dc26fda9251d056208746aeadadd", "task_id": "emo_Fear-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.04574969410896301, "target_z": -0.4511718727163813, "ce": 6.062326908111572, "genuineness": 4.582659721374512, "identity": 0.6061012744903564, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/fr/5b562c155deebeb3c2ddf448.mp3" }, { "key": "original-emo_Fear-fr-0-seed1702-scale1.0", "bucket": "emo_Fear", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "0a7a6e8bb4fc68d340e0d6449371a678f6a92a6a5b9a74d84b4e6fafeb40c64f", "task_id": "emo_Fear-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.02065873146057129, "target_z": -0.49218751522412446, "ce": 5.808161735534668, "genuineness": 3.973883628845215, "identity": 0.5824587941169739, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/fr/d352feb514962476acace799.mp3" }, { "key": "original-emo_Fear-fr-1-seed1701-scale0.0", "bucket": "emo_Fear", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "f2ceaf533dbbb493293b4fb3fea74a4ea747079483221fa77cf030d175e1d3e4", "task_id": "emo_Fear-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": -0.0008477866649627686, "target_z": -0.5273437454327626, "ce": 6.284721851348877, "genuineness": 4.632867813110352, "identity": 0.7996858358383179, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/fr/56a0eff5a5ebd54bc4c0e4a7.mp3" }, { "key": "original-emo_Fear-fr-1-seed1701-scale0.5", "bucket": "emo_Fear", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "5c4c41707a738f6195129a73ceebe9ca917f770bf2e85d2a02679154a795f2b0", "task_id": "emo_Fear-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.01707431674003601, "target_z": -0.4980468788060311, "ce": 6.165581703186035, "genuineness": 4.632867813110352, "identity": 0.7673152089118958, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre, nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/fr/5bcf6493969d5cbe0d8759db.mp3" }, { "key": "original-emo_Fear-fr-1-seed1701-scale0.75", "bucket": "emo_Fear", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "0a1799ad487a6e471ab3bc04e616c9fa04bf9c18b8085066dd1319148c4dd403", "task_id": "emo_Fear-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.04455488920211792, "target_z": -0.4531249939103502, "ce": 6.070269584655762, "genuineness": 4.507347106933594, "identity": 0.7155944108963013, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/fr/c1783812d288728a45abcbd9.mp3" }, { "key": "original-emo_Fear-fr-1-seed1701-scale1.0", "bucket": "emo_Fear", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "c0dc608a4cee3ead67259fead77c505c3ae614208ee875ef97a89d80b9c89385", "task_id": "emo_Fear-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.03141200542449951, "target_z": -0.4746093757612062, "ce": 6.2767791748046875, "genuineness": 4.494794845581055, "identity": 0.717261552810669, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/fr/98f8818a714177f5c1209675.mp3" }, { "key": "original-emo_Fear-fr-1-seed1702-scale0.0", "bucket": "emo_Fear", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "1210716c225f91520cf00f6f8f22f459f1a64d96be7626918342e85421d02fcb", "task_id": "emo_Fear-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.011100292205810547, "target_z": -0.5078124847758756, "ce": 6.141753673553467, "genuineness": 4.557555198669434, "identity": 0.8036926984786987, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/fr/3fa19ffad5d0e04089f3cc0c.mp3" }, { "key": "original-emo_Fear-fr-1-seed1702-scale0.5", "bucket": "emo_Fear", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "9efd536ff642a4205a89956be8c6767f827e042dc2f6a001877ba9f4bba526c7", "task_id": "emo_Fear-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.04574969410896301, "target_z": -0.4511718727163813, "ce": 6.109982967376709, "genuineness": 4.532451152801514, "identity": 0.6900439262390137, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/fr/b6321afaf9574fd4b970bcf1.mp3" }, { "key": "original-emo_Fear-fr-1-seed1702-scale0.75", "bucket": "emo_Fear", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "bc979c60a0b07efa385482159e55f5545382bd603f1677dda23f79025990d81a", "task_id": "emo_Fear-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": -0.010406255722045898, "target_z": -0.542968763701712, "ce": 6.292664527893066, "genuineness": 4.582659721374512, "identity": 0.6745560765266418, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/fr/1ddc4e0508bcb1973533004b.mp3" }, { "key": "original-emo_Fear-fr-1-seed1702-scale1.0", "bucket": "emo_Fear", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "b9a6bb45b9793e495cb22c31a64b4e9f7a89dc530f148e0f090897ddb9b1fd15", "task_id": "emo_Fear-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.015879511833190918, "target_z": -0.5, "ce": 5.974957466125488, "genuineness": 4.469690799713135, "identity": 0.645412802696228, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/fr/84bd5e477c6fdf8d076ce367.mp3" }, { "key": "original-emo_Fear-nl-0-seed1701-scale0.0", "bucket": "emo_Fear", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "878d27a57056d152705c45cac5934252ce9ce75837e7d4dd28cff1ceee7b7d92", "task_id": "emo_Fear-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.0624769926071167, "target_z": -0.4238281272836187, "ce": 6.078212261199951, "genuineness": 4.193545341491699, "identity": 0.5468001961708069, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/nl/b6d2c2a74401407b37bc7054.mp3" }, { "key": "original-emo_Fear-nl-0-seed1701-scale0.5", "bucket": "emo_Fear", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "c56b5d52f2cf542c371b5504f8afdeca94d19531d451bc671496fced0940ed14", "task_id": "emo_Fear-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.08159391582012177, "target_z": -0.3925781151043191, "ce": 6.117925643920898, "genuineness": 4.080576419830322, "identity": 0.6542661190032959, "hypothesis": "De deur 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_Fear/nl/f512b65e286cca29ddbd3d20.mp3" }, { "key": "original-emo_Fear-nl-0-seed1701-scale0.75", "bucket": "emo_Fear", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "69eae66cc54aee2cca75b62aafbcef8852a6b40b3bf74589d1995a7cbc75a2e5", "task_id": "emo_Fear-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.11146408319473267, "target_z": -0.34375001217929957, "ce": 5.967014789581299, "genuineness": 4.15588903427124, "identity": 0.7091823816299438, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/nl/21b3da0bf9f7c923686b9682.mp3" }, { "key": "original-emo_Fear-nl-0-seed1701-scale1.0", "bucket": "emo_Fear", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "987aadacc4685bacfac2c1da1f1282440bd12a5fe46a7326d4365091de6662d8", "task_id": "emo_Fear-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.11265890300273895, "target_z": -0.34179686662673153, "ce": 6.125868320465088, "genuineness": 4.306513786315918, "identity": 0.4861898422241211, "hypothesis": "De deur 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_Fear/nl/a7d1db9d1a03dfed2144369e.mp3" }, { "key": "original-emo_Fear-nl-0-seed1702-scale0.0", "bucket": "emo_Fear", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "86dc3b70de8b11c50e86276611a82d0a5e3f07650f172b68dff715d11189edd2", "task_id": "emo_Fear-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.05769777297973633, "target_z": -0.4316406120594942, "ce": 6.078212261199951, "genuineness": 3.898571252822876, "identity": 0.6577631235122681, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/nl/c4ba4d8ac757d8ae0868bd7a.mp3" }, { "key": "original-emo_Fear-nl-0-seed1702-scale0.5", "bucket": "emo_Fear", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "76fbe777b672d29c287ed28131d861a8868bbc8d5d25a832563f2810d3578716", "task_id": "emo_Fear-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.1939057856798172, "target_z": -0.208984381850856, "ce": 6.078212261199951, "genuineness": 4.20609712600708, "identity": 0.7269761562347412, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/nl/191132b3d32f02c097cc3095.mp3" }, { "key": "original-emo_Fear-nl-0-seed1702-scale0.75", "bucket": "emo_Fear", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "bc43129df347e091499e32df99cf0d30efef05e45dd387085ccb5df52d7eeece", "task_id": "emo_Fear-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.07442507147789001, "target_z": -0.40429686662673153, "ce": 5.863759994506836, "genuineness": 4.344170093536377, "identity": 0.6208299994468689, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/nl/24bcb8fa98e45db430b10467.mp3" }, { "key": "original-emo_Fear-nl-0-seed1702-scale1.0", "bucket": "emo_Fear", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "e2ef832b56ca680eba0cf9dd0e6e2e4b304bf4e26e939bd8c25ccaa1f4828b9f", "task_id": "emo_Fear-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.0923471748828888, "target_z": -0.375, "ce": 5.982900142669678, "genuineness": 4.149612903594971, "identity": 0.2455243468284607, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/nl/66da2339d36956cbe415fad3.mp3" }, { "key": "original-emo_Fear-nl-1-seed1701-scale0.0", "bucket": "emo_Fear", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "405e4dbc529c69e0bdb9fec217e8c45cd2be4d16d15be99f055e976e0c582ca7", "task_id": "emo_Fear-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.04336008429527283, "target_z": -0.4550781151043191, "ce": 6.054384231567383, "genuineness": 4.3504462242126465, "identity": 0.5720974802970886, "hypothesis": "Ik 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_Fear/nl/9c14112074e2e5c4da7eb50e.mp3" }, { "key": "original-emo_Fear-nl-1-seed1701-scale0.5", "bucket": "emo_Fear", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "aa49f8b495a14c48929689433668683aaff73937dda02c5e0ccf10356ea28c0f", "task_id": "emo_Fear-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.04574969410896301, "target_z": -0.4511718727163813, "ce": 6.149696350097656, "genuineness": 4.545003414154053, "identity": 0.5824989080429077, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/nl/1090d05a4f3e7d7227730904.mp3" }, { "key": "original-emo_Fear-nl-1-seed1701-scale0.75", "bucket": "emo_Fear", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "b2090f2edde21aaa58f0ce8b40312564aa976519309a59b5aeb72f4e493d2755", "task_id": "emo_Fear-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.06964585185050964, "target_z": -0.4121093514026071, "ce": 6.221180438995361, "genuineness": 4.331617832183838, "identity": 0.6296426653862, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/nl/87d5d4f5dfaec712772313f8.mp3" }, { "key": "original-emo_Fear-nl-1-seed1701-scale1.0", "bucket": "emo_Fear", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "26678f2847b08b48ec9430d9002afeafccc49b24c417d326074e380f31694c4a", "task_id": "emo_Fear-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.01707431674003601, "target_z": -0.4980468788060311, "ce": 6.173524379730225, "genuineness": 4.369274139404297, "identity": 0.3930965065956116, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/nl/c56f5956c3c1aadda34e3f9a.mp3" }, { "key": "original-emo_Fear-nl-1-seed1702-scale0.0", "bucket": "emo_Fear", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "0e15e02da41ab7308711f9f94fda6e11a328a1a7eab6f44c44700a5120ff5592", "task_id": "emo_Fear-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.04574969410896301, "target_z": -0.4511718727163813, "ce": 6.252951145172119, "genuineness": 4.256305694580078, "identity": 0.7582176923751831, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/nl/2811810400de82a356ce857b.mp3" }, { "key": "original-emo_Fear-nl-1-seed1702-scale0.5", "bucket": "emo_Fear", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "a08e02a04beb0a75d7249948b5df00874e86658e9f6c6285d638d7b2ae8345d2", "task_id": "emo_Fear-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.03858083486557007, "target_z": -0.4628906485973929, "ce": 6.213237762451172, "genuineness": 4.20609712600708, "identity": 0.7805421352386475, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/nl/cc1cea9a038fa8ddd93b15fb.mp3" }, { "key": "original-emo_Fear-nl-1-seed1702-scale0.75", "bucket": "emo_Fear", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "ced341b1339486e937ccb5360965a7c482a8e0e1970f7dd48355be8961f5f69f", "task_id": "emo_Fear-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.08756794035434723, "target_z": -0.3828125091344747, "ce": 6.268836498260498, "genuineness": 4.419482707977295, "identity": 0.7230693101882935, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/nl/a336cbf091185649bd5c0dfc.mp3" }, { "key": "original-emo_Fear-nl-1-seed1702-scale1.0", "bucket": "emo_Fear", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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 Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "a55bb27c9a29263a73d235c561ca17bd09c4673cd9030de7736c08edb37d5727", "mp3_sha256": "cf0cb8c078954fb2c665807aa2a0878575642ef4eaa9d95b1bb91e93f704e805", "task_id": "emo_Fear-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Fear. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Fear. 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 Fear. 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 Fear. 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": 0.037386029958724976, "target_z": -0.46484376979136177, "ce": 6.268836498260498, "genuineness": 4.532451152801514, "identity": 0.6553423404693604, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Fear/nl/8779b1bc2a0ed142a949023d.mp3" } ], "source_standard_audio_unchanged": true }